Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3540 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.9292. Min Act: -0.1700
Data Index: 971183 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.7104. Min Act: -0.1700
Data Index: 3380584 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.6792. Min Act: -0.1700
Data Index: 3396121 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.6167. Min Act: -0.1700
Data Index: 4708798 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.4604. Min Act: -0.1700
Data Index: 7421702 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.4604. Min Act: -0.1700
Data Index: 6866059 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.3979. Min Act: -0.1700
Data Index: 8020322 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.4292. Min Act: -0.1700
Data Index: 8614465 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.4292. Min Act: -0.1700
Data Index: 4880039 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.3979. Min Act: -0.1700
Data Index: 5163425 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.3979. Min Act: -0.1700
Data Index: 2204420 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.3979. Min Act: -0.1700
Data Index: 2835634 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.3667. Min Act: -0.1700
Data Index: 4975165 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.3667. Min Act: -0.1700
Data Index: 314002 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.3979. Min Act: -0.1700
Data Index: 3480234 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.3667. Min Act: -0.1700
Data Index: 1323109 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.3667. Min Act: -0.1700
Data Index: 1952451 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.3354. Min Act: -0.1700
Data Index: 5040909 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.3354. Min Act: -0.1700
Data Index: 7177327 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.3354. Min Act: -0.1700
Data Index: 1561606 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19