Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1503 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7291. Min Range: -6.7291
Max Act: 6.6979. Min Act: -0.1700
Data Index: 7166276 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7291. Min Range: -6.7291
Max Act: 6.7291. Min Act: -0.1700
Data Index: 1461518 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7291. Min Range: -6.7291
Max Act: 6.6354. Min Act: -0.1700
Data Index: 152968 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7291. Min Range: -6.7291
Max Act: 6.3854. Min Act: -0.1700
Data Index: 4048844 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7291. Min Range: -6.7291
Max Act: 6.3229. Min Act: -0.1700
Data Index: 3151877 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7291. Min Range: -6.7291
Max Act: 6.3541. Min Act: -0.1700
Data Index: 8016217 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7291. Min Range: -6.7291
Max Act: 6.3541. Min Act: -0.1700
Data Index: 2411024 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7291. Min Range: -6.7291
Max Act: 6.2916. Min Act: -0.1700
Data Index: 6737065 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7291. Min Range: -6.7291
Max Act: 6.3229. Min Act: -0.1700
Data Index: 8567952 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7291. Min Range: -6.7291
Max Act: 6.2916. Min Act: -0.1700
Data Index: 4591804 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7291. Min Range: -6.7291
Max Act: 6.2291. Min Act: -0.1700
Data Index: 449697 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7291. Min Range: -6.7291
Max Act: 6.1666. Min Act: -0.1700
Data Index: 7284282 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7291. Min Range: -6.7291
Max Act: 6.1354. Min Act: -0.1700
Data Index: 3161492 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7291. Min Range: -6.7291
Max Act: 6.1041. Min Act: -0.1700
Data Index: 6432419 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7291. Min Range: -6.7291
Max Act: 6.1041. Min Act: -0.1700
Data Index: 3756329 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7291. Min Range: -6.7291
Max Act: 6.0416. Min Act: -0.1700
Data Index: 4356427 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7291. Min Range: -6.7291
Max Act: 6.0416. Min Act: -0.1700
Data Index: 4639207 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7291. Min Range: -6.7291
Max Act: 6.0416. Min Act: -0.1700
Data Index: 7554651 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7291. Min Range: -6.7291
Max Act: 6.0104. Min Act: -0.1700
Data Index: 6498190 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7291. Min Range: -6.7291
Max Act: 5.9791. Min Act: -0.1700
Data Index: 4765237 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19