Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4631 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2201. Min Range: -4.2201
Max Act: 4.2201. Min Act: -0.1700
Data Index: 6472349 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2201. Min Range: -4.2201
Max Act: 4.1264. Min Act: -0.1700
Data Index: 2628359 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2201. Min Range: -4.2201
Max Act: 4.1264. Min Act: -0.1700
Data Index: 147829 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2201. Min Range: -4.2201
Max Act: 4.0638. Min Act: -0.1700
Data Index: 8124595 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2201. Min Range: -4.2201
Max Act: 4.0326. Min Act: -0.1700
Data Index: 127441 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2201. Min Range: -4.2201
Max Act: 4.0326. Min Act: -0.1700
Data Index: 6032414 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2201. Min Range: -4.2201
Max Act: 4.0326. Min Act: -0.1700
Data Index: 2628360 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2201. Min Range: -4.2201
Max Act: 4.0638. Min Act: -0.1700
Data Index: 2628356 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2201. Min Range: -4.2201
Max Act: 4.0326. Min Act: -0.1700
Data Index: 6032412 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2201. Min Range: -4.2201
Max Act: 4.0326. Min Act: -0.1700
Data Index: 2455174 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2201. Min Range: -4.2201
Max Act: 4.0013. Min Act: -0.1700
Data Index: 4428164 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2201. Min Range: -4.2201
Max Act: 4.0013. Min Act: -0.1700
Data Index: 1288246 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2201. Min Range: -4.2201
Max Act: 4.0013. Min Act: -0.1700
Data Index: 1911127 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2201. Min Range: -4.2201
Max Act: 4.0013. Min Act: -0.1700
Data Index: 1769529 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2201. Min Range: -4.2201
Max Act: 3.9701. Min Act: -0.1700
Data Index: 660376 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2201. Min Range: -4.2201
Max Act: 3.9701. Min Act: -0.1700
Data Index: 3881557 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2201. Min Range: -4.2201
Max Act: 3.9701. Min Act: -0.1700
Data Index: 2889572 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2201. Min Range: -4.2201
Max Act: 3.9701. Min Act: -0.1700
Data Index: 7006547 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2201. Min Range: -4.2201
Max Act: 4.0013. Min Act: -0.1700
Data Index: 2628362 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2201. Min Range: -4.2201
Max Act: 3.9701. Min Act: -0.1700
Data Index: 7830636 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19