Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3454 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5339. Min Range: -2.5339
Max Act: 2.5339. Min Act: -0.1700
Data Index: 2405385 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5339. Min Range: -2.5339
Max Act: 2.5177. Min Act: -0.1700
Data Index: 3880778 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5339. Min Range: -2.5339
Max Act: 2.5016. Min Act: -0.1700
Data Index: 7499698 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5339. Min Range: -2.5339
Max Act: 2.4529. Min Act: -0.1700
Data Index: 1015500 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5339. Min Range: -2.5339
Max Act: 2.4529. Min Act: -0.1700
Data Index: 3677024 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5339. Min Range: -2.5339
Max Act: 2.4529. Min Act: -0.1700
Data Index: 8623611 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5339. Min Range: -2.5339
Max Act: 2.4203. Min Act: -0.1700
Data Index: 2980096 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5339. Min Range: -2.5339
Max Act: 2.4203. Min Act: -0.1700
Data Index: 2259323 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5339. Min Range: -2.5339
Max Act: 2.4203. Min Act: -0.1700
Data Index: 8281125 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5339. Min Range: -2.5339
Max Act: 2.3877. Min Act: -0.1700
Data Index: 1187302 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5339. Min Range: -2.5339
Max Act: 2.3877. Min Act: -0.1700
Data Index: 5199459 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5339. Min Range: -2.5339
Max Act: 2.3713. Min Act: -0.1700
Data Index: 4777865 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5339. Min Range: -2.5339
Max Act: 2.3713. Min Act: -0.1700
Data Index: 5984671 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5339. Min Range: -2.5339
Max Act: 2.3550. Min Act: -0.1700
Data Index: 1080002 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5339. Min Range: -2.5339
Max Act: 2.3550. Min Act: -0.1700
Data Index: 1739515 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5339. Min Range: -2.5339
Max Act: 2.3550. Min Act: -0.1700
Data Index: 4544298 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5339. Min Range: -2.5339
Max Act: 2.3057. Min Act: -0.1700
Data Index: 8335545 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5339. Min Range: -2.5339
Max Act: 2.3057. Min Act: -0.1700
Data Index: 4352267 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5339. Min Range: -2.5339
Max Act: 2.3222. Min Act: -0.1700
Data Index: 8164633 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5339. Min Range: -2.5339
Max Act: 2.2893. Min Act: -0.1700
Data Index: 7250451 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19