Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1678 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0420. Min Range: -5.0420
Max Act: 5.0420. Min Act: -0.1700
Data Index: 5431413 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0420. Min Range: -5.0420
Max Act: 4.9170. Min Act: -0.1700
Data Index: 112160 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0420. Min Range: -5.0420
Max Act: 4.8233. Min Act: -0.1700
Data Index: 5948398 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0420. Min Range: -5.0420
Max Act: 4.8545. Min Act: -0.1700
Data Index: 6064263 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0420. Min Range: -5.0420
Max Act: 4.8545. Min Act: -0.1700
Data Index: 8421085 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0420. Min Range: -5.0420
Max Act: 4.8233. Min Act: -0.1700
Data Index: 4036663 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0420. Min Range: -5.0420
Max Act: 4.8233. Min Act: -0.1700
Data Index: 5849579 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0420. Min Range: -5.0420
Max Act: 4.7920. Min Act: -0.1700
Data Index: 7782990 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0420. Min Range: -5.0420
Max Act: 4.7920. Min Act: -0.1700
Data Index: 5918780 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0420. Min Range: -5.0420
Max Act: 4.7920. Min Act: -0.1700
Data Index: 1010034 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0420. Min Range: -5.0420
Max Act: 4.7920. Min Act: -0.1700
Data Index: 226645 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0420. Min Range: -5.0420
Max Act: 4.7920. Min Act: -0.1700
Data Index: 6942711 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0420. Min Range: -5.0420
Max Act: 4.7920. Min Act: -0.1700
Data Index: 92854 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0420. Min Range: -5.0420
Max Act: 4.7920. Min Act: -0.1700
Data Index: 6351510 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0420. Min Range: -5.0420
Max Act: 4.7920. Min Act: -0.1700
Data Index: 3611847 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0420. Min Range: -5.0420
Max Act: 4.7920. Min Act: -0.1700
Data Index: 1885767 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0420. Min Range: -5.0420
Max Act: 4.7608. Min Act: -0.1700
Data Index: 812278 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0420. Min Range: -5.0420
Max Act: 4.7608. Min Act: -0.1700
Data Index: 1237708 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0420. Min Range: -5.0420
Max Act: 4.7295. Min Act: -0.1700
Data Index: 4753348 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0420. Min Range: -5.0420
Max Act: 4.7920. Min Act: -0.1700
Data Index: 1190780 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19