Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3297 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9416. Min Range: -4.9416
Max Act: 4.9416. Min Act: -0.1700
Data Index: 99162 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9416. Min Range: -4.9416
Max Act: 4.8791. Min Act: -0.1700
Data Index: 1987291 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9416. Min Range: -4.9416
Max Act: 4.8166. Min Act: -0.1700
Data Index: 6518629 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9416. Min Range: -4.9416
Max Act: 4.8478. Min Act: -0.1700
Data Index: 118091 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9416. Min Range: -4.9416
Max Act: 4.7853. Min Act: -0.1700
Data Index: 2877621 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9416. Min Range: -4.9416
Max Act: 4.7541. Min Act: -0.1700
Data Index: 895999 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9416. Min Range: -4.9416
Max Act: 4.7541. Min Act: -0.1700
Data Index: 3964845 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9416. Min Range: -4.9416
Max Act: 4.7541. Min Act: -0.1700
Data Index: 733410 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9416. Min Range: -4.9416
Max Act: 4.7228. Min Act: -0.1700
Data Index: 7807083 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9416. Min Range: -4.9416
Max Act: 4.7541. Min Act: -0.1700
Data Index: 1835197 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9416. Min Range: -4.9416
Max Act: 4.6916. Min Act: -0.1700
Data Index: 2860204 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9416. Min Range: -4.9416
Max Act: 4.7228. Min Act: -0.1700
Data Index: 7841045 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9416. Min Range: -4.9416
Max Act: 4.7228. Min Act: -0.1700
Data Index: 93631 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9416. Min Range: -4.9416
Max Act: 4.6603. Min Act: -0.1700
Data Index: 6461983 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9416. Min Range: -4.9416
Max Act: 4.6291. Min Act: -0.1700
Data Index: 503730 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9416. Min Range: -4.9416
Max Act: 4.6603. Min Act: -0.1700
Data Index: 7284416 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9416. Min Range: -4.9416
Max Act: 4.6291. Min Act: -0.1700
Data Index: 4267313 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9416. Min Range: -4.9416
Max Act: 4.6291. Min Act: -0.1700
Data Index: 1311043 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9416. Min Range: -4.9416
Max Act: 4.5978. Min Act: -0.1700
Data Index: 1107593 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9416. Min Range: -4.9416
Max Act: 4.6291. Min Act: -0.1700
Data Index: 2456451 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19