Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2647 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3663. Min Range: -10.3663
Max Act: 10.3663. Min Act: -0.1700
Data Index: 3690296 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3663. Min Range: -10.3663
Max Act: 10.0538. Min Act: -0.1700
Data Index: 2143264 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3663. Min Range: -10.3663
Max Act: 9.9288. Min Act: -0.1700
Data Index: 5050006 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3663. Min Range: -10.3663
Max Act: 9.8663. Min Act: -0.1700
Data Index: 7341406 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3663. Min Range: -10.3663
Max Act: 9.8663. Min Act: -0.1700
Data Index: 2460620 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3663. Min Range: -10.3663
Max Act: 9.8663. Min Act: -0.1700
Data Index: 6390042 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3663. Min Range: -10.3663
Max Act: 9.8038. Min Act: -0.1700
Data Index: 5543201 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3663. Min Range: -10.3663
Max Act: 9.8038. Min Act: -0.1700
Data Index: 3260982 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3663. Min Range: -10.3663
Max Act: 9.7413. Min Act: -0.1700
Data Index: 5691965 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3663. Min Range: -10.3663
Max Act: 9.7413. Min Act: -0.1700
Data Index: 498192 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3663. Min Range: -10.3663
Max Act: 9.6788. Min Act: -0.1700
Data Index: 4322521 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3663. Min Range: -10.3663
Max Act: 9.6788. Min Act: -0.1700
Data Index: 134207 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3663. Min Range: -10.3663
Max Act: 9.6163. Min Act: -0.1700
Data Index: 3800568 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3663. Min Range: -10.3663
Max Act: 9.6788. Min Act: -0.1700
Data Index: 6056440 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3663. Min Range: -10.3663
Max Act: 9.6163. Min Act: -0.1700
Data Index: 3645461 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3663. Min Range: -10.3663
Max Act: 9.5538. Min Act: -0.1700
Data Index: 5773909 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3663. Min Range: -10.3663
Max Act: 9.6163. Min Act: -0.1700
Data Index: 4225648 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3663. Min Range: -10.3663
Max Act: 9.6163. Min Act: -0.1700
Data Index: 8619709 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3663. Min Range: -10.3663
Max Act: 9.5538. Min Act: -0.1700
Data Index: 4034392 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3663. Min Range: -10.3663
Max Act: 9.5538. Min Act: -0.1700
Data Index: 1238503 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19