Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3388 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3264. Min Range: -4.3264
Max Act: 4.3264. Min Act: -0.1700
Data Index: 2034371 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3264. Min Range: -4.3264
Max Act: 4.1701. Min Act: -0.1700
Data Index: 6411315 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3264. Min Range: -4.3264
Max Act: 4.1389. Min Act: -0.1700
Data Index: 8040808 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3264. Min Range: -4.3264
Max Act: 4.1076. Min Act: -0.1700
Data Index: 941276 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3264. Min Range: -4.3264
Max Act: 4.1389. Min Act: -0.1700
Data Index: 621280 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3264. Min Range: -4.3264
Max Act: 4.0764. Min Act: -0.1700
Data Index: 6612235 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3264. Min Range: -4.3264
Max Act: 4.0764. Min Act: -0.1700
Data Index: 906113 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3264. Min Range: -4.3264
Max Act: 4.0451. Min Act: -0.1700
Data Index: 1813768 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3264. Min Range: -4.3264
Max Act: 4.0451. Min Act: -0.1700
Data Index: 8228216 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3264. Min Range: -4.3264
Max Act: 4.0451. Min Act: -0.1700
Data Index: 1515861 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3264. Min Range: -4.3264
Max Act: 4.0138. Min Act: -0.1700
Data Index: 6892478 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3264. Min Range: -4.3264
Max Act: 3.9826. Min Act: -0.1700
Data Index: 3590424 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3264. Min Range: -4.3264
Max Act: 3.9513. Min Act: -0.1700
Data Index: 6988323 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3264. Min Range: -4.3264
Max Act: 3.9513. Min Act: -0.1700
Data Index: 1147878 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3264. Min Range: -4.3264
Max Act: 3.9513. Min Act: -0.1700
Data Index: 2983721 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3264. Min Range: -4.3264
Max Act: 3.9200. Min Act: -0.1700
Data Index: 2279092 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3264. Min Range: -4.3264
Max Act: 3.9513. Min Act: -0.1700
Data Index: 1925652 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3264. Min Range: -4.3264
Max Act: 3.9200. Min Act: -0.1700
Data Index: 2034370 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3264. Min Range: -4.3264
Max Act: 3.9200. Min Act: -0.1700
Data Index: 4945713 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3264. Min Range: -4.3264
Max Act: 3.9200. Min Act: -0.1700
Data Index: 7484507 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19