Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0153. Min Range: -6.0153
Max Act: 6.0153. Min Act: -0.1700
Data Index: 1895300 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0153. Min Range: -6.0153
Max Act: 5.8903. Min Act: -0.1700
Data Index: 7629616 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0153. Min Range: -6.0153
Max Act: 5.8278. Min Act: -0.1700
Data Index: 7687703 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0153. Min Range: -6.0153
Max Act: 5.8590. Min Act: -0.1700
Data Index: 6725023 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0153. Min Range: -6.0153
Max Act: 5.8278. Min Act: -0.1700
Data Index: 7265905 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0153. Min Range: -6.0153
Max Act: 5.8278. Min Act: -0.1700
Data Index: 7360281 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0153. Min Range: -6.0153
Max Act: 5.7653. Min Act: -0.1700
Data Index: 2180549 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0153. Min Range: -6.0153
Max Act: 5.7340. Min Act: -0.1700
Data Index: 1818131 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0153. Min Range: -6.0153
Max Act: 5.7340. Min Act: -0.1700
Data Index: 1784147 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0153. Min Range: -6.0153
Max Act: 5.7340. Min Act: -0.1700
Data Index: 2431778 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0153. Min Range: -6.0153
Max Act: 5.7340. Min Act: -0.1700
Data Index: 818413 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0153. Min Range: -6.0153
Max Act: 5.7028. Min Act: -0.1700
Data Index: 2160259 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0153. Min Range: -6.0153
Max Act: 5.7028. Min Act: -0.1700
Data Index: 6725024 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0153. Min Range: -6.0153
Max Act: 5.7028. Min Act: -0.1700
Data Index: 5939502 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0153. Min Range: -6.0153
Max Act: 5.7028. Min Act: -0.1700
Data Index: 2877196 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0153. Min Range: -6.0153
Max Act: 5.7028. Min Act: -0.1700
Data Index: 4085147 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0153. Min Range: -6.0153
Max Act: 5.6715. Min Act: -0.1700
Data Index: 3094992 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0153. Min Range: -6.0153
Max Act: 5.6715. Min Act: -0.1700
Data Index: 6557945 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0153. Min Range: -6.0153
Max Act: 5.6715. Min Act: -0.1700
Data Index: 3392398 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0153. Min Range: -6.0153
Max Act: 5.6403. Min Act: -0.1700
Data Index: 5541558 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19