Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6370 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8342. Min Range: -6.8342
Max Act: 6.8029. Min Act: -0.1700
Data Index: 7349225 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8342. Min Range: -6.8342
Max Act: 6.8342. Min Act: -0.1700
Data Index: 4369253 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8342. Min Range: -6.8342
Max Act: 6.7717. Min Act: -0.1700
Data Index: 6410705 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8342. Min Range: -6.8342
Max Act: 6.7717. Min Act: -0.1700
Data Index: 243947 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8342. Min Range: -6.8342
Max Act: 6.7404. Min Act: -0.1700
Data Index: 5888469 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8342. Min Range: -6.8342
Max Act: 6.7092. Min Act: -0.1700
Data Index: 5943275 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8342. Min Range: -6.8342
Max Act: 6.6779. Min Act: -0.1700
Data Index: 3446401 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8342. Min Range: -6.8342
Max Act: 6.6467. Min Act: -0.1700
Data Index: 5906996 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8342. Min Range: -6.8342
Max Act: 6.6467. Min Act: -0.1700
Data Index: 3446402 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8342. Min Range: -6.8342
Max Act: 6.6154. Min Act: -0.1700
Data Index: 3971135 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8342. Min Range: -6.8342
Max Act: 6.5529. Min Act: -0.1700
Data Index: 4671683 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8342. Min Range: -6.8342
Max Act: 6.5217. Min Act: -0.1700
Data Index: 7501526 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8342. Min Range: -6.8342
Max Act: 6.5217. Min Act: -0.1700
Data Index: 6659740 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8342. Min Range: -6.8342
Max Act: 6.5217. Min Act: -0.1700
Data Index: 1177084 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8342. Min Range: -6.8342
Max Act: 6.4592. Min Act: -0.1700
Data Index: 577386 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8342. Min Range: -6.8342
Max Act: 6.4904. Min Act: -0.1700
Data Index: 898554 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8342. Min Range: -6.8342
Max Act: 6.4592. Min Act: -0.1700
Data Index: 3426766 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8342. Min Range: -6.8342
Max Act: 6.4904. Min Act: -0.1700
Data Index: 3320366 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8342. Min Range: -6.8342
Max Act: 6.4592. Min Act: -0.1700
Data Index: 5502759 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8342. Min Range: -6.8342
Max Act: 6.4592. Min Act: -0.1700
Data Index: 268055 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19