Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3518 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7220. Min Range: -2.7220
Max Act: 2.7220. Min Act: -0.1700
Data Index: 4364090 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7220. Min Range: -2.7220
Max Act: 2.6740. Min Act: -0.1700
Data Index: 3982635 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7220. Min Range: -2.7220
Max Act: 2.6740. Min Act: -0.1700
Data Index: 5165641 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7220. Min Range: -2.7220
Max Act: 2.6579. Min Act: -0.1700
Data Index: 3091384 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7220. Min Range: -2.7220
Max Act: 2.6419. Min Act: -0.1700
Data Index: 8114980 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7220. Min Range: -2.7220
Max Act: 2.6258. Min Act: -0.1700
Data Index: 3857113 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7220. Min Range: -2.7220
Max Act: 2.6419. Min Act: -0.1700
Data Index: 6731504 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7220. Min Range: -2.7220
Max Act: 2.6097. Min Act: -0.1700
Data Index: 2300194 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7220. Min Range: -2.7220
Max Act: 2.6097. Min Act: -0.1700
Data Index: 7320414 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7220. Min Range: -2.7220
Max Act: 2.6097. Min Act: -0.1700
Data Index: 44353 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7220. Min Range: -2.7220
Max Act: 2.6097. Min Act: -0.1700
Data Index: 3466535 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7220. Min Range: -2.7220
Max Act: 2.6097. Min Act: -0.1700
Data Index: 3607183 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7220. Min Range: -2.7220
Max Act: 2.6097. Min Act: -0.1700
Data Index: 2470276 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7220. Min Range: -2.7220
Max Act: 2.6097. Min Act: -0.1700
Data Index: 6198207 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7220. Min Range: -2.7220
Max Act: 2.6097. Min Act: -0.1700
Data Index: 8487505 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7220. Min Range: -2.7220
Max Act: 2.5937. Min Act: -0.1700
Data Index: 7947078 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7220. Min Range: -2.7220
Max Act: 2.6097. Min Act: -0.1700
Data Index: 3581887 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7220. Min Range: -2.7220
Max Act: 2.5775. Min Act: -0.1700
Data Index: 1920311 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7220. Min Range: -2.7220
Max Act: 2.5937. Min Act: -0.1700
Data Index: 778187 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7220. Min Range: -2.7220
Max Act: 2.5937. Min Act: -0.1700
Data Index: 83562 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19