Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3408 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6434. Min Range: -3.6434
Max Act: 3.6434. Min Act: -0.1656
Data Index: 3262479 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6434. Min Range: -3.6434
Max Act: 3.6278. Min Act: -0.1533
Data Index: 4903156 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6434. Min Range: -3.6434
Max Act: 3.6278. Min Act: -0.1201
Data Index: 4958580 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6434. Min Range: -3.6434
Max Act: 3.5808. Min Act: -0.1673
Data Index: 6968230 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6434. Min Range: -3.6434
Max Act: 3.5652. Min Act: -0.1317
Data Index: 198708 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6434. Min Range: -3.6434
Max Act: 3.5965. Min Act: -0.1674
Data Index: 5415132 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6434. Min Range: -3.6434
Max Act: 3.5495. Min Act: -0.1640
Data Index: 2373567 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6434. Min Range: -3.6434
Max Act: 3.5652. Min Act: -0.1475
Data Index: 2641342 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6434. Min Range: -3.6434
Max Act: 3.5182. Min Act: -0.1388
Data Index: 537558 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6434. Min Range: -3.6434
Max Act: 3.5495. Min Act: -0.1606
Data Index: 1977752 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6434. Min Range: -3.6434
Max Act: 3.5339. Min Act: -0.1690
Data Index: 4264886 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6434. Min Range: -3.6434
Max Act: 3.5339. Min Act: -0.1687
Data Index: 6560329 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6434. Min Range: -3.6434
Max Act: 3.5339. Min Act: -0.1594
Data Index: 2492057 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6434. Min Range: -3.6434
Max Act: 3.5339. Min Act: -0.1632
Data Index: 1475062 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6434. Min Range: -3.6434
Max Act: 3.5495. Min Act: -0.0688
Data Index: 6459192 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6434. Min Range: -3.6434
Max Act: 3.5339. Min Act: -0.1566
Data Index: 5013953 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6434. Min Range: -3.6434
Max Act: 3.5182. Min Act: -0.0033
Data Index: 6898854 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6434. Min Range: -3.6434
Max Act: 3.5339. Min Act: -0.0630
Data Index: 7969382 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6434. Min Range: -3.6434
Max Act: 3.5339. Min Act: -0.1269
Data Index: 4604945 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6434. Min Range: -3.6434
Max Act: 3.5182. Min Act: -0.1259
Data Index: 6924498 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19