Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4031 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8322. Min Range: -3.8322
Max Act: 3.8322. Min Act: -0.1700
Data Index: 4335168 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8322. Min Range: -3.8322
Max Act: 3.6288. Min Act: -0.1700
Data Index: 1835636 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8322. Min Range: -3.8322
Max Act: 3.5975. Min Act: -0.1700
Data Index: 190966 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8322. Min Range: -3.8322
Max Act: 3.5975. Min Act: -0.1700
Data Index: 2521865 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8322. Min Range: -3.8322
Max Act: 3.5192. Min Act: -0.1700
Data Index: 7097512 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8322. Min Range: -3.8322
Max Act: 3.5036. Min Act: -0.1700
Data Index: 6019049 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8322. Min Range: -3.8322
Max Act: 3.4879. Min Act: -0.1700
Data Index: 6983336 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8322. Min Range: -3.8322
Max Act: 3.4096. Min Act: -0.1700
Data Index: 2298779 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8322. Min Range: -3.8322
Max Act: 3.3625. Min Act: -0.1700
Data Index: 2393807 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8322. Min Range: -3.8322
Max Act: 3.3311. Min Act: -0.1700
Data Index: 4038571 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8322. Min Range: -3.8322
Max Act: 3.3311. Min Act: -0.1700
Data Index: 3413230 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8322. Min Range: -3.8322
Max Act: 3.2998. Min Act: -0.1700
Data Index: 4038572 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8322. Min Range: -3.8322
Max Act: 3.3154. Min Act: -0.1700
Data Index: 7833888 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8322. Min Range: -3.8322
Max Act: 3.2840. Min Act: -0.1700
Data Index: 7655536 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8322. Min Range: -3.8322
Max Act: 3.2683. Min Act: -0.1700
Data Index: 6985532 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8322. Min Range: -3.8322
Max Act: 3.2526. Min Act: -0.1700
Data Index: 7017062 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8322. Min Range: -3.8322
Max Act: 3.2840. Min Act: -0.1700
Data Index: 5940517 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8322. Min Range: -3.8322
Max Act: 3.2526. Min Act: -0.1700
Data Index: 3760334 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8322. Min Range: -3.8322
Max Act: 3.2369. Min Act: -0.1700
Data Index: 3695730 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8322. Min Range: -3.8322
Max Act: 3.2369. Min Act: -0.1700
Data Index: 1981165 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19