Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4412 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8310. Min Range: -3.8310
Max Act: 3.8310. Min Act: -0.1700
Data Index: 1103051 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8310. Min Range: -3.8310
Max Act: 3.6277. Min Act: -0.1700
Data Index: 8524437 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8310. Min Range: -3.8310
Max Act: 3.5181. Min Act: -0.1700
Data Index: 6972979 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8310. Min Range: -3.8310
Max Act: 3.4868. Min Act: -0.1700
Data Index: 6115362 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8310. Min Range: -3.8310
Max Act: 3.4711. Min Act: -0.1700
Data Index: 3401632 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8310. Min Range: -3.8310
Max Act: 3.4398. Min Act: -0.1700
Data Index: 3755249 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8310. Min Range: -3.8310
Max Act: 3.4084. Min Act: -0.1700
Data Index: 866938 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8310. Min Range: -3.8310
Max Act: 3.4084. Min Act: -0.1700
Data Index: 4708870 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8310. Min Range: -3.8310
Max Act: 3.3927. Min Act: -0.1700
Data Index: 6764966 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8310. Min Range: -3.8310
Max Act: 3.3927. Min Act: -0.1700
Data Index: 5818050 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8310. Min Range: -3.8310
Max Act: 3.4084. Min Act: -0.1700
Data Index: 7515662 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8310. Min Range: -3.8310
Max Act: 3.3614. Min Act: -0.1700
Data Index: 798254 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8310. Min Range: -3.8310
Max Act: 3.3614. Min Act: -0.1700
Data Index: 3084536 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8310. Min Range: -3.8310
Max Act: 3.3457. Min Act: -0.1700
Data Index: 7015544 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8310. Min Range: -3.8310
Max Act: 3.3300. Min Act: -0.1700
Data Index: 1047615 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8310. Min Range: -3.8310
Max Act: 3.3457. Min Act: -0.1700
Data Index: 6537690 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8310. Min Range: -3.8310
Max Act: 3.3457. Min Act: -0.1700
Data Index: 5297937 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8310. Min Range: -3.8310
Max Act: 3.3300. Min Act: -0.1700
Data Index: 7909650 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8310. Min Range: -3.8310
Max Act: 3.3457. Min Act: -0.1700
Data Index: 6021565 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8310. Min Range: -3.8310
Max Act: 3.3143. Min Act: -0.1700
Data Index: 6694895 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19