Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4268 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6454. Min Range: -3.6454
Max Act: 3.6454. Min Act: -0.1700
Data Index: 6170436 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6454. Min Range: -3.6454
Max Act: 3.5358. Min Act: -0.1700
Data Index: 8037276 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6454. Min Range: -3.6454
Max Act: 3.3791. Min Act: -0.1700
Data Index: 5011603 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6454. Min Range: -3.6454
Max Act: 3.3320. Min Act: -0.1700
Data Index: 8087145 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6454. Min Range: -3.6454
Max Act: 3.3320. Min Act: -0.1700
Data Index: 314694 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6454. Min Range: -3.6454
Max Act: 3.3320. Min Act: -0.1700
Data Index: 6589546 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6454. Min Range: -3.6454
Max Act: 3.3320. Min Act: -0.1700
Data Index: 1999288 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6454. Min Range: -3.6454
Max Act: 3.3164. Min Act: -0.1700
Data Index: 4708076 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6454. Min Range: -3.6454
Max Act: 3.3007. Min Act: -0.1700
Data Index: 481424 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6454. Min Range: -3.6454
Max Act: 3.3007. Min Act: -0.1700
Data Index: 8133186 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6454. Min Range: -3.6454
Max Act: 3.2850. Min Act: -0.1700
Data Index: 4335802 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6454. Min Range: -3.6454
Max Act: 3.2850. Min Act: -0.1700
Data Index: 3374068 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6454. Min Range: -3.6454
Max Act: 3.2850. Min Act: -0.1700
Data Index: 709982 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6454. Min Range: -3.6454
Max Act: 3.2850. Min Act: -0.1700
Data Index: 8483041 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6454. Min Range: -3.6454
Max Act: 3.2535. Min Act: -0.1700
Data Index: 4777207 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6454. Min Range: -3.6454
Max Act: 3.2535. Min Act: -0.1700
Data Index: 6631434 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6454. Min Range: -3.6454
Max Act: 3.2221. Min Act: -0.1700
Data Index: 785021 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6454. Min Range: -3.6454
Max Act: 3.2064. Min Act: -0.1700
Data Index: 2181673 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6454. Min Range: -3.6454
Max Act: 3.2064. Min Act: -0.1700
Data Index: 131226 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6454. Min Range: -3.6454
Max Act: 3.2064. Min Act: -0.1700
Data Index: 5663372 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19