Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4457 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7919. Min Range: -4.7919
Max Act: 4.7919. Min Act: -0.1700
Data Index: 6826430 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7919. Min Range: -4.7919
Max Act: 4.7606. Min Act: -0.1700
Data Index: 3875758 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7919. Min Range: -4.7919
Max Act: 4.7606. Min Act: -0.1700
Data Index: 360765 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7919. Min Range: -4.7919
Max Act: 4.7606. Min Act: -0.1700
Data Index: 7190280 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7919. Min Range: -4.7919
Max Act: 4.7919. Min Act: -0.1700
Data Index: 7047642 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7919. Min Range: -4.7919
Max Act: 4.7294. Min Act: -0.1700
Data Index: 8362442 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7919. Min Range: -4.7919
Max Act: 4.6669. Min Act: -0.1700
Data Index: 2558685 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7919. Min Range: -4.7919
Max Act: 4.6981. Min Act: -0.1700
Data Index: 7331839 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7919. Min Range: -4.7919
Max Act: 4.6981. Min Act: -0.1700
Data Index: 6141012 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7919. Min Range: -4.7919
Max Act: 4.6981. Min Act: -0.1699
Data Index: 6942163 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7919. Min Range: -4.7919
Max Act: 4.6669. Min Act: -0.1700
Data Index: 296572 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7919. Min Range: -4.7919
Max Act: 4.6669. Min Act: -0.1700
Data Index: 3627610 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7919. Min Range: -4.7919
Max Act: 4.6669. Min Act: -0.1700
Data Index: 4595370 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7919. Min Range: -4.7919
Max Act: 4.6669. Min Act: -0.1700
Data Index: 6082292 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7919. Min Range: -4.7919
Max Act: 4.6669. Min Act: -0.1700
Data Index: 8029377 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7919. Min Range: -4.7919
Max Act: 4.6981. Min Act: -0.1700
Data Index: 1820907 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7919. Min Range: -4.7919
Max Act: 4.6356. Min Act: -0.1700
Data Index: 4196825 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7919. Min Range: -4.7919
Max Act: 4.6669. Min Act: -0.1700
Data Index: 4072534 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7919. Min Range: -4.7919
Max Act: 4.6356. Min Act: -0.1700
Data Index: 232017 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7919. Min Range: -4.7919
Max Act: 4.6356. Min Act: -0.1700
Data Index: 5068525 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19