Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2227 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 11.9404. Min Range: -11.9404
Max Act: 11.9404. Min Act: -0.1700
Data Index: 7767389 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9404. Min Range: -11.9404
Max Act: 11.6279. Min Act: -0.1700
Data Index: 729490 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9404. Min Range: -11.9404
Max Act: 11.5654. Min Act: -0.1700
Data Index: 475532 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9404. Min Range: -11.9404
Max Act: 11.5029. Min Act: -0.1700
Data Index: 6200554 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9404. Min Range: -11.9404
Max Act: 11.4404. Min Act: -0.1700
Data Index: 8658639 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9404. Min Range: -11.9404
Max Act: 11.2529. Min Act: -0.1700
Data Index: 1307495 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9404. Min Range: -11.9404
Max Act: 11.2529. Min Act: -0.1700
Data Index: 7765663 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9404. Min Range: -11.9404
Max Act: 11.0654. Min Act: -0.1700
Data Index: 3616835 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9404. Min Range: -11.9404
Max Act: 11.0654. Min Act: -0.1700
Data Index: 2018768 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9404. Min Range: -11.9404
Max Act: 11.0029. Min Act: -0.1700
Data Index: 2482014 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9404. Min Range: -11.9404
Max Act: 10.9404. Min Act: -0.1700
Data Index: 4062170 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9404. Min Range: -11.9404
Max Act: 10.8779. Min Act: -0.1700
Data Index: 2857334 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9404. Min Range: -11.9404
Max Act: 10.8779. Min Act: -0.1700
Data Index: 8159174 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9404. Min Range: -11.9404
Max Act: 10.8779. Min Act: -0.1700
Data Index: 8335747 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9404. Min Range: -11.9404
Max Act: 10.8154. Min Act: -0.1700
Data Index: 1762458 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9404. Min Range: -11.9404
Max Act: 10.8154. Min Act: -0.1700
Data Index: 4915084 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9404. Min Range: -11.9404
Max Act: 10.8779. Min Act: -0.1700
Data Index: 1127614 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9404. Min Range: -11.9404
Max Act: 10.7529. Min Act: -0.1700
Data Index: 2500263 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9404. Min Range: -11.9404
Max Act: 10.7529. Min Act: -0.1700
Data Index: 2577147 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9404. Min Range: -11.9404
Max Act: 10.6904. Min Act: -0.1700
Data Index: 6884662 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19