Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2097 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.8155. Min Act: -0.1700
Data Index: 7907071 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.7677. Min Act: -0.1700
Data Index: 2585054 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.7038. Min Act: -0.1700
Data Index: 792135 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.6878. Min Act: -0.1700
Data Index: 5969909 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.6878. Min Act: -0.1700
Data Index: 1478331 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.6557. Min Act: -0.1700
Data Index: 707125 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.6397. Min Act: -0.1700
Data Index: 380300 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.6075. Min Act: -0.1700
Data Index: 2042385 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.6236. Min Act: -0.1700
Data Index: 7098679 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.5914. Min Act: -0.1700
Data Index: 8435155 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.5914. Min Act: -0.1700
Data Index: 8412350 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.5753. Min Act: -0.1700
Data Index: 1439623 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.5753. Min Act: -0.1700
Data Index: 2397598 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.5753. Min Act: -0.1700
Data Index: 2673833 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.5592. Min Act: -0.1700
Data Index: 8271767 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.5592. Min Act: -0.1700
Data Index: 3998997 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.5592. Min Act: -0.1700
Data Index: 2994421 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.5430. Min Act: -0.1700
Data Index: 5799136 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.5430. Min Act: -0.1700
Data Index: 7132699 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8155. Min Range: -2.8155
Max Act: 2.5430. Min Act: -0.1700
Data Index: 6075920 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19