Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4157 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6241. Min Range: -7.6241
Max Act: 7.6241. Min Act: -0.1700
Data Index: 151972 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6241. Min Range: -7.6241
Max Act: 7.3116. Min Act: -0.1700
Data Index: 1096188 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6241. Min Range: -7.6241
Max Act: 7.2491. Min Act: -0.1700
Data Index: 5615399 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6241. Min Range: -7.6241
Max Act: 7.2178. Min Act: -0.1700
Data Index: 7555366 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6241. Min Range: -7.6241
Max Act: 7.2491. Min Act: -0.1700
Data Index: 4842504 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6241. Min Range: -7.6241
Max Act: 7.2491. Min Act: -0.1700
Data Index: 5860385 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6241. Min Range: -7.6241
Max Act: 7.1553. Min Act: -0.1700
Data Index: 2035445 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6241. Min Range: -7.6241
Max Act: 7.1866. Min Act: -0.1700
Data Index: 1436012 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6241. Min Range: -7.6241
Max Act: 7.1866. Min Act: -0.1700
Data Index: 8511074 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6241. Min Range: -7.6241
Max Act: 7.0928. Min Act: -0.1700
Data Index: 2256205 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6241. Min Range: -7.6241
Max Act: 7.1241. Min Act: -0.1700
Data Index: 319620 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6241. Min Range: -7.6241
Max Act: 7.0928. Min Act: -0.1700
Data Index: 1528381 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6241. Min Range: -7.6241
Max Act: 7.0616. Min Act: -0.1700
Data Index: 5603996 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6241. Min Range: -7.6241
Max Act: 7.0616. Min Act: -0.1700
Data Index: 8756190 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6241. Min Range: -7.6241
Max Act: 7.0303. Min Act: -0.1700
Data Index: 3695554 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6241. Min Range: -7.6241
Max Act: 7.0616. Min Act: -0.1700
Data Index: 1238816 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6241. Min Range: -7.6241
Max Act: 7.0303. Min Act: -0.1700
Data Index: 309528 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6241. Min Range: -7.6241
Max Act: 7.0303. Min Act: -0.1700
Data Index: 8527295 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6241. Min Range: -7.6241
Max Act: 6.9991. Min Act: -0.1700
Data Index: 6916462 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6241. Min Range: -7.6241
Max Act: 6.9991. Min Act: -0.1700
Data Index: 8380542 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19