Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3884 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6844. Min Range: -6.6844
Max Act: 6.6844. Min Act: -0.1700
Data Index: 5476725 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6844. Min Range: -6.6844
Max Act: 6.2156. Min Act: -0.1700
Data Index: 7116746 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6844. Min Range: -6.6844
Max Act: 6.1531. Min Act: -0.1700
Data Index: 3320199 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6844. Min Range: -6.6844
Max Act: 6.0594. Min Act: -0.1700
Data Index: 1102617 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6844. Min Range: -6.6844
Max Act: 6.0281. Min Act: -0.1700
Data Index: 6121906 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6844. Min Range: -6.6844
Max Act: 5.9969. Min Act: -0.1700
Data Index: 6133878 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6844. Min Range: -6.6844
Max Act: 6.0281. Min Act: -0.1700
Data Index: 3419909 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6844. Min Range: -6.6844
Max Act: 6.0281. Min Act: -0.1700
Data Index: 8394507 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6844. Min Range: -6.6844
Max Act: 5.9969. Min Act: -0.1700
Data Index: 805215 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6844. Min Range: -6.6844
Max Act: 5.9969. Min Act: -0.1700
Data Index: 3777379 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6844. Min Range: -6.6844
Max Act: 5.9656. Min Act: -0.1700
Data Index: 2032636 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6844. Min Range: -6.6844
Max Act: 5.9656. Min Act: -0.1700
Data Index: 1458783 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6844. Min Range: -6.6844
Max Act: 5.9344. Min Act: -0.1700
Data Index: 498595 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6844. Min Range: -6.6844
Max Act: 5.9344. Min Act: -0.1700
Data Index: 7446755 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6844. Min Range: -6.6844
Max Act: 5.9344. Min Act: -0.1700
Data Index: 507706 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6844. Min Range: -6.6844
Max Act: 5.9344. Min Act: -0.1700
Data Index: 7178624 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6844. Min Range: -6.6844
Max Act: 5.9344. Min Act: -0.1700
Data Index: 4045581 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6844. Min Range: -6.6844
Max Act: 5.9031. Min Act: -0.1700
Data Index: 2412789 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6844. Min Range: -6.6844
Max Act: 5.9031. Min Act: -0.1700
Data Index: 2399435 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6844. Min Range: -6.6844
Max Act: 5.9344. Min Act: -0.1700
Data Index: 2750987 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19