Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 795 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9669. Min Range: -3.9669
Max Act: 3.9669. Min Act: -0.1700
Data Index: 2745024 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9669. Min Range: -3.9669
Max Act: 3.9357. Min Act: -0.1687
Data Index: 4455656 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9669. Min Range: -3.9669
Max Act: 3.9357. Min Act: -0.1700
Data Index: 5061542 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9669. Min Range: -3.9669
Max Act: 3.9044. Min Act: -0.1700
Data Index: 8461388 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9669. Min Range: -3.9669
Max Act: 3.9044. Min Act: -0.1700
Data Index: 8559103 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9669. Min Range: -3.9669
Max Act: 3.9044. Min Act: -0.1700
Data Index: 7550137 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9669. Min Range: -3.9669
Max Act: 3.9044. Min Act: -0.1699
Data Index: 2258872 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9669. Min Range: -3.9669
Max Act: 3.8732. Min Act: -0.1700
Data Index: 2498671 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9669. Min Range: -3.9669
Max Act: 3.8732. Min Act: -0.1700
Data Index: 5742998 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9669. Min Range: -3.9669
Max Act: 3.8732. Min Act: -0.1700
Data Index: 4052066 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9669. Min Range: -3.9669
Max Act: 3.8732. Min Act: -0.1700
Data Index: 51068 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9669. Min Range: -3.9669
Max Act: 3.8732. Min Act: -0.1700
Data Index: 6804391 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9669. Min Range: -3.9669
Max Act: 3.8106. Min Act: -0.1700
Data Index: 138992 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9669. Min Range: -3.9669
Max Act: 3.8732. Min Act: -0.1700
Data Index: 4297634 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9669. Min Range: -3.9669
Max Act: 3.8419. Min Act: -0.1700
Data Index: 2876417 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9669. Min Range: -3.9669
Max Act: 3.8419. Min Act: -0.1700
Data Index: 228885 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9669. Min Range: -3.9669
Max Act: 3.8419. Min Act: -0.1700
Data Index: 3446489 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9669. Min Range: -3.9669
Max Act: 3.8419. Min Act: -0.1700
Data Index: 6514262 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9669. Min Range: -3.9669
Max Act: 3.8419. Min Act: -0.1700
Data Index: 6236507 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9669. Min Range: -3.9669
Max Act: 3.8419. Min Act: -0.1700
Data Index: 4387282 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19