Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4311 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8106. Min Range: -6.8106
Max Act: 6.8106. Min Act: -0.1700
Data Index: 8591588 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8106. Min Range: -6.8106
Max Act: 6.8106. Min Act: -0.1700
Data Index: 3050265 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8106. Min Range: -6.8106
Max Act: 6.7169. Min Act: -0.1700
Data Index: 6012404 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8106. Min Range: -6.8106
Max Act: 6.6544. Min Act: -0.1700
Data Index: 2186575 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8106. Min Range: -6.8106
Max Act: 6.5919. Min Act: -0.1700
Data Index: 7209686 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8106. Min Range: -6.8106
Max Act: 6.5606. Min Act: -0.1700
Data Index: 4427085 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8106. Min Range: -6.8106
Max Act: 6.5606. Min Act: -0.1700
Data Index: 4034973 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8106. Min Range: -6.8106
Max Act: 6.5919. Min Act: -0.1700
Data Index: 7031792 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8106. Min Range: -6.8106
Max Act: 6.4981. Min Act: -0.1700
Data Index: 5363651 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8106. Min Range: -6.8106
Max Act: 6.5294. Min Act: -0.1700
Data Index: 2902441 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8106. Min Range: -6.8106
Max Act: 6.5606. Min Act: -0.1700
Data Index: 915583 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8106. Min Range: -6.8106
Max Act: 6.5294. Min Act: -0.1700
Data Index: 8031993 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8106. Min Range: -6.8106
Max Act: 6.4981. Min Act: -0.1700
Data Index: 221979 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8106. Min Range: -6.8106
Max Act: 6.4669. Min Act: -0.1700
Data Index: 3571934 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8106. Min Range: -6.8106
Max Act: 6.4981. Min Act: -0.1700
Data Index: 4164982 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8106. Min Range: -6.8106
Max Act: 6.4981. Min Act: -0.1700
Data Index: 560374 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8106. Min Range: -6.8106
Max Act: 6.4669. Min Act: -0.1700
Data Index: 2585407 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8106. Min Range: -6.8106
Max Act: 6.4981. Min Act: -0.1700
Data Index: 5869135 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8106. Min Range: -6.8106
Max Act: 6.4981. Min Act: -0.1700
Data Index: 5847323 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8106. Min Range: -6.8106
Max Act: 6.4981. Min Act: -0.1700
Data Index: 3678057 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19