Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 46 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1428. Min Range: -4.1428
Max Act: 4.1428. Min Act: -0.1700
Data Index: 2701225 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1428. Min Range: -4.1428
Max Act: 4.0490. Min Act: -0.1700
Data Index: 6496528 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1428. Min Range: -4.1428
Max Act: 4.0177. Min Act: -0.1700
Data Index: 2409500 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1428. Min Range: -4.1428
Max Act: 3.9865. Min Act: -0.1700
Data Index: 5829255 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1428. Min Range: -4.1428
Max Act: 3.9865. Min Act: -0.1700
Data Index: 6681415 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1428. Min Range: -4.1428
Max Act: 3.9865. Min Act: -0.1700
Data Index: 4552011 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1428. Min Range: -4.1428
Max Act: 4.0177. Min Act: -0.1700
Data Index: 1751343 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1428. Min Range: -4.1428
Max Act: 3.9865. Min Act: -0.1700
Data Index: 8254290 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1428. Min Range: -4.1428
Max Act: 3.9865. Min Act: -0.1700
Data Index: 7006421 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1428. Min Range: -4.1428
Max Act: 3.9552. Min Act: -0.1700
Data Index: 987669 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1428. Min Range: -4.1428
Max Act: 3.9552. Min Act: -0.1700
Data Index: 4245129 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1428. Min Range: -4.1428
Max Act: 3.9865. Min Act: -0.1700
Data Index: 5110591 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1428. Min Range: -4.1428
Max Act: 3.9552. Min Act: -0.1700
Data Index: 2110948 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1428. Min Range: -4.1428
Max Act: 3.9552. Min Act: -0.1700
Data Index: 3670839 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1428. Min Range: -4.1428
Max Act: 3.9552. Min Act: -0.1700
Data Index: 6236692 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1428. Min Range: -4.1428
Max Act: 3.9239. Min Act: -0.1700
Data Index: 6303671 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1428. Min Range: -4.1428
Max Act: 3.9552. Min Act: -0.1700
Data Index: 6370564 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1428. Min Range: -4.1428
Max Act: 3.9552. Min Act: -0.1700
Data Index: 1120432 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1428. Min Range: -4.1428
Max Act: 3.9552. Min Act: -0.1700
Data Index: 6502083 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1428. Min Range: -4.1428
Max Act: 3.9239. Min Act: -0.1700
Data Index: 6615971 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19