Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3937 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8844. Min Range: -1.8844
Max Act: 1.8844. Min Act: -0.1700
Data Index: 1687285 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8844. Min Range: -1.8844
Max Act: 1.8502. Min Act: -0.1700
Data Index: 2640297 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8844. Min Range: -1.8844
Max Act: 1.8416. Min Act: -0.1700
Data Index: 7489886 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8844. Min Range: -1.8844
Max Act: 1.8158. Min Act: -0.1700
Data Index: 370793 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8844. Min Range: -1.8844
Max Act: 1.8158. Min Act: -0.1700
Data Index: 7759601 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8844. Min Range: -1.8844
Max Act: 1.7900. Min Act: -0.1700
Data Index: 2868137 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8844. Min Range: -1.8844
Max Act: 1.7814. Min Act: -0.1700
Data Index: 7552108 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8844. Min Range: -1.8844
Max Act: 1.7728. Min Act: -0.1700
Data Index: 3339816 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8844. Min Range: -1.8844
Max Act: 1.7728. Min Act: -0.1700
Data Index: 3683170 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8844. Min Range: -1.8844
Max Act: 1.7556. Min Act: -0.1700
Data Index: 1193862 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8844. Min Range: -1.8844
Max Act: 1.7642. Min Act: -0.1700
Data Index: 1522128 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8844. Min Range: -1.8844
Max Act: 1.7556. Min Act: -0.1700
Data Index: 2213288 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8844. Min Range: -1.8844
Max Act: 1.7469. Min Act: -0.1700
Data Index: 6823422 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8844. Min Range: -1.8844
Max Act: 1.7556. Min Act: -0.1700
Data Index: 8829774 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8844. Min Range: -1.8844
Max Act: 1.7383. Min Act: -0.1700
Data Index: 2645940 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8844. Min Range: -1.8844
Max Act: 1.7556. Min Act: -0.1700
Data Index: 6975848 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8844. Min Range: -1.8844
Max Act: 1.7469. Min Act: -0.1700
Data Index: 4602522 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8844. Min Range: -1.8844
Max Act: 1.7469. Min Act: -0.1700
Data Index: 2979772 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8844. Min Range: -1.8844
Max Act: 1.7383. Min Act: -0.1700
Data Index: 7426630 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8844. Min Range: -1.8844
Max Act: 1.7296. Min Act: -0.1700
Data Index: 1808545 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19