Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5990 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8879. Min Range: -3.8879
Max Act: 3.8566. Min Act: -0.1700
Data Index: 371786 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8879. Min Range: -3.8879
Max Act: 3.8879. Min Act: -0.1700
Data Index: 4969707 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8879. Min Range: -3.8879
Max Act: 3.7941. Min Act: -0.1700
Data Index: 254463 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8879. Min Range: -3.8879
Max Act: 3.7472. Min Act: -0.1700
Data Index: 8266290 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8879. Min Range: -3.8879
Max Act: 3.7315. Min Act: -0.1700
Data Index: 5563175 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8879. Min Range: -3.8879
Max Act: 3.7315. Min Act: -0.1700
Data Index: 8117705 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8879. Min Range: -3.8879
Max Act: 3.7159. Min Act: -0.1700
Data Index: 1194415 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8879. Min Range: -3.8879
Max Act: 3.7159. Min Act: -0.1700
Data Index: 8772907 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8879. Min Range: -3.8879
Max Act: 3.6846. Min Act: -0.1700
Data Index: 6792816 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8879. Min Range: -3.8879
Max Act: 3.6846. Min Act: -0.1700
Data Index: 5831612 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8879. Min Range: -3.8879
Max Act: 3.6846. Min Act: -0.1700
Data Index: 1042405 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8879. Min Range: -3.8879
Max Act: 3.6690. Min Act: -0.1700
Data Index: 1352790 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8879. Min Range: -3.8879
Max Act: 3.6690. Min Act: -0.1700
Data Index: 1824649 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8879. Min Range: -3.8879
Max Act: 3.6533. Min Act: -0.1700
Data Index: 8603270 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8879. Min Range: -3.8879
Max Act: 3.6533. Min Act: -0.1700
Data Index: 5598392 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8879. Min Range: -3.8879
Max Act: 3.6377. Min Act: -0.1700
Data Index: 3326704 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8879. Min Range: -3.8879
Max Act: 3.6377. Min Act: -0.1700
Data Index: 5256753 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8879. Min Range: -3.8879
Max Act: 3.6220. Min Act: -0.1700
Data Index: 424132 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8879. Min Range: -3.8879
Max Act: 3.6220. Min Act: -0.1700
Data Index: 1599542 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8879. Min Range: -3.8879
Max Act: 3.6064. Min Act: -0.1700
Data Index: 192721 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19