Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4409 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6123. Min Range: -5.6123
Max Act: 5.6123. Min Act: -0.1700
Data Index: 2490620 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6123. Min Range: -5.6123
Max Act: 5.6123. Min Act: -0.1700
Data Index: 8090704 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6123. Min Range: -5.6123
Max Act: 5.6123. Min Act: -0.1700
Data Index: 681919 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6123. Min Range: -5.6123
Max Act: 5.5810. Min Act: -0.1700
Data Index: 3789078 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6123. Min Range: -5.6123
Max Act: 5.5810. Min Act: -0.1700
Data Index: 6865279 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6123. Min Range: -5.6123
Max Act: 5.5810. Min Act: -0.1700
Data Index: 5533204 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6123. Min Range: -5.6123
Max Act: 5.5498. Min Act: -0.1700
Data Index: 214896 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6123. Min Range: -5.6123
Max Act: 5.5498. Min Act: -0.1700
Data Index: 6861270 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6123. Min Range: -5.6123
Max Act: 5.5185. Min Act: -0.1700
Data Index: 806342 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6123. Min Range: -5.6123
Max Act: 5.5498. Min Act: -0.1700
Data Index: 3029392 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6123. Min Range: -5.6123
Max Act: 5.5185. Min Act: -0.1700
Data Index: 1684572 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6123. Min Range: -5.6123
Max Act: 5.5185. Min Act: -0.1700
Data Index: 2200564 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6123. Min Range: -5.6123
Max Act: 5.5185. Min Act: -0.1700
Data Index: 6811435 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6123. Min Range: -5.6123
Max Act: 5.4873. Min Act: -0.1700
Data Index: 3655456 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6123. Min Range: -5.6123
Max Act: 5.4873. Min Act: -0.1700
Data Index: 593251 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6123. Min Range: -5.6123
Max Act: 5.4560. Min Act: -0.1700
Data Index: 4414266 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6123. Min Range: -5.6123
Max Act: 5.4873. Min Act: -0.1700
Data Index: 3846182 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6123. Min Range: -5.6123
Max Act: 5.4873. Min Act: -0.1700
Data Index: 2656430 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6123. Min Range: -5.6123
Max Act: 5.4873. Min Act: -0.1700
Data Index: 5494908 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6123. Min Range: -5.6123
Max Act: 5.4248. Min Act: -0.1700
Data Index: 7406146 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19