Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3024 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4828. Min Range: -3.4828
Max Act: 3.4828. Min Act: -0.1700
Data Index: 4847250 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4828. Min Range: -3.4828
Max Act: 3.4358. Min Act: -0.1700
Data Index: 4891919 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4828. Min Range: -3.4828
Max Act: 3.4201. Min Act: -0.1700
Data Index: 3503394 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4828. Min Range: -3.4828
Max Act: 3.3574. Min Act: -0.1700
Data Index: 2852863 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4828. Min Range: -3.4828
Max Act: 3.3260. Min Act: -0.1700
Data Index: 874442 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4828. Min Range: -3.4828
Max Act: 3.3260. Min Act: -0.1700
Data Index: 7832455 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4828. Min Range: -3.4828
Max Act: 3.3103. Min Act: -0.1700
Data Index: 8070625 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4828. Min Range: -3.4828
Max Act: 3.2789. Min Act: -0.1700
Data Index: 2835532 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4828. Min Range: -3.4828
Max Act: 3.2789. Min Act: -0.1700
Data Index: 1315767 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4828. Min Range: -3.4828
Max Act: 3.2632. Min Act: -0.1700
Data Index: 8070612 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4828. Min Range: -3.4828
Max Act: 3.2475. Min Act: -0.1700
Data Index: 8177700 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4828. Min Range: -3.4828
Max Act: 3.2475. Min Act: -0.1700
Data Index: 8070636 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4828. Min Range: -3.4828
Max Act: 3.2318. Min Act: -0.1700
Data Index: 8707649 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4828. Min Range: -3.4828
Max Act: 3.2161. Min Act: -0.1700
Data Index: 6716309 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4828. Min Range: -3.4828
Max Act: 3.2161. Min Act: -0.1700
Data Index: 4438276 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4828. Min Range: -3.4828
Max Act: 3.2318. Min Act: -0.1700
Data Index: 2864087 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4828. Min Range: -3.4828
Max Act: 3.2632. Min Act: -0.1700
Data Index: 97741 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4828. Min Range: -3.4828
Max Act: 3.2318. Min Act: -0.1700
Data Index: 3675445 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4828. Min Range: -3.4828
Max Act: 3.2161. Min Act: -0.1700
Data Index: 2674446 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4828. Min Range: -3.4828
Max Act: 3.2161. Min Act: -0.1700
Data Index: 4121309 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19