Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2920 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8317. Min Range: -4.8317
Max Act: 4.8317. Min Act: -0.1700
Data Index: 8138614 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8317. Min Range: -4.8317
Max Act: 4.8005. Min Act: -0.1700
Data Index: 2660516 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8317. Min Range: -4.8317
Max Act: 4.8005. Min Act: -0.1700
Data Index: 1334109 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8317. Min Range: -4.8317
Max Act: 4.8005. Min Act: -0.1700
Data Index: 7094576 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8317. Min Range: -4.8317
Max Act: 4.8005. Min Act: -0.1700
Data Index: 3471745 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8317. Min Range: -4.8317
Max Act: 4.6442. Min Act: -0.1700
Data Index: 416250 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8317. Min Range: -4.8317
Max Act: 4.6130. Min Act: -0.1700
Data Index: 1243054 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8317. Min Range: -4.8317
Max Act: 4.5817. Min Act: -0.1700
Data Index: 7760285 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8317. Min Range: -4.8317
Max Act: 4.5817. Min Act: -0.1700
Data Index: 4993965 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8317. Min Range: -4.8317
Max Act: 4.5192. Min Act: -0.1700
Data Index: 2104963 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8317. Min Range: -4.8317
Max Act: 4.4880. Min Act: -0.1700
Data Index: 6215771 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8317. Min Range: -4.8317
Max Act: 4.4567. Min Act: -0.1700
Data Index: 5052661 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8317. Min Range: -4.8317
Max Act: 4.4567. Min Act: -0.1700
Data Index: 7984037 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8317. Min Range: -4.8317
Max Act: 4.4567. Min Act: -0.1700
Data Index: 7018191 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8317. Min Range: -4.8317
Max Act: 4.4567. Min Act: -0.1700
Data Index: 6795301 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8317. Min Range: -4.8317
Max Act: 4.4567. Min Act: -0.1700
Data Index: 1034171 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8317. Min Range: -4.8317
Max Act: 4.4567. Min Act: -0.1700
Data Index: 8823360 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8317. Min Range: -4.8317
Max Act: 4.4255. Min Act: -0.1700
Data Index: 656399 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8317. Min Range: -4.8317
Max Act: 4.4255. Min Act: -0.1700
Data Index: 3470418 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8317. Min Range: -4.8317
Max Act: 4.3942. Min Act: -0.1700
Data Index: 7358275 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19