Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 361 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4285. Min Range: -8.4285
Max Act: 8.4285. Min Act: -0.1700
Data Index: 17294 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4285. Min Range: -8.4285
Max Act: 8.3035. Min Act: -0.1700
Data Index: 7914523 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4285. Min Range: -8.4285
Max Act: 8.1785. Min Act: -0.1700
Data Index: 1749235 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4285. Min Range: -8.4285
Max Act: 8.1160. Min Act: -0.1700
Data Index: 3929381 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4285. Min Range: -8.4285
Max Act: 8.1160. Min Act: -0.1700
Data Index: 6967061 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4285. Min Range: -8.4285
Max Act: 8.1160. Min Act: -0.1700
Data Index: 7346044 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4285. Min Range: -8.4285
Max Act: 8.1160. Min Act: -0.1700
Data Index: 3468124 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4285. Min Range: -8.4285
Max Act: 8.1160. Min Act: -0.1700
Data Index: 2684764 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4285. Min Range: -8.4285
Max Act: 8.1160. Min Act: -0.1700
Data Index: 6866845 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4285. Min Range: -8.4285
Max Act: 8.0535. Min Act: -0.1700
Data Index: 6955259 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4285. Min Range: -8.4285
Max Act: 7.9910. Min Act: -0.1700
Data Index: 3536863 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4285. Min Range: -8.4285
Max Act: 8.0535. Min Act: -0.1700
Data Index: 3893453 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4285. Min Range: -8.4285
Max Act: 7.9910. Min Act: -0.1700
Data Index: 7945992 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4285. Min Range: -8.4285
Max Act: 7.9910. Min Act: -0.1700
Data Index: 6383514 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4285. Min Range: -8.4285
Max Act: 7.9910. Min Act: -0.1700
Data Index: 5869337 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4285. Min Range: -8.4285
Max Act: 7.9910. Min Act: -0.1700
Data Index: 5477932 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4285. Min Range: -8.4285
Max Act: 7.9910. Min Act: -0.1700
Data Index: 3030946 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4285. Min Range: -8.4285
Max Act: 7.9285. Min Act: -0.1700
Data Index: 5990454 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4285. Min Range: -8.4285
Max Act: 7.9285. Min Act: -0.1700
Data Index: 6446235 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4285. Min Range: -8.4285
Max Act: 7.9285. Min Act: -0.1700
Data Index: 5064903 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19