Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3379 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7695. Min Range: -8.7695
Max Act: 8.7695. Min Act: -0.1700
Data Index: 428725 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7695. Min Range: -8.7695
Max Act: 8.2695. Min Act: -0.1700
Data Index: 7286258 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7695. Min Range: -8.7695
Max Act: 8.3320. Min Act: -0.1700
Data Index: 4810001 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7695. Min Range: -8.7695
Max Act: 8.2070. Min Act: -0.1700
Data Index: 3578539 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7695. Min Range: -8.7695
Max Act: 8.2070. Min Act: -0.1700
Data Index: 1155131 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7695. Min Range: -8.7695
Max Act: 8.0195. Min Act: -0.1700
Data Index: 5817133 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7695. Min Range: -8.7695
Max Act: 7.9570. Min Act: -0.1700
Data Index: 369897 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7695. Min Range: -8.7695
Max Act: 7.7695. Min Act: -0.1700
Data Index: 4631445 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7695. Min Range: -8.7695
Max Act: 7.7695. Min Act: -0.1700
Data Index: 7787067 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7695. Min Range: -8.7695
Max Act: 7.7695. Min Act: -0.1700
Data Index: 6652155 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7695. Min Range: -8.7695
Max Act: 7.7070. Min Act: -0.1700
Data Index: 5503626 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7695. Min Range: -8.7695
Max Act: 7.7070. Min Act: -0.1700
Data Index: 302365 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7695. Min Range: -8.7695
Max Act: 7.5820. Min Act: -0.1700
Data Index: 6893589 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7695. Min Range: -8.7695
Max Act: 7.5508. Min Act: -0.1700
Data Index: 7921463 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7695. Min Range: -8.7695
Max Act: 7.5195. Min Act: -0.1700
Data Index: 4593000 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7695. Min Range: -8.7695
Max Act: 7.5195. Min Act: -0.1700
Data Index: 5617228 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7695. Min Range: -8.7695
Max Act: 7.5195. Min Act: -0.1700
Data Index: 5115958 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7695. Min Range: -8.7695
Max Act: 7.4883. Min Act: -0.1700
Data Index: 3217476 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7695. Min Range: -8.7695
Max Act: 7.4883. Min Act: -0.1700
Data Index: 102125 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7695. Min Range: -8.7695
Max Act: 7.4570. Min Act: -0.1700
Data Index: 7766372 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19