Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3440 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3236. Min Range: -7.3236
Max Act: 7.3236. Min Act: -0.1700
Data Index: 3400746 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3236. Min Range: -7.3236
Max Act: 7.1361. Min Act: -0.1700
Data Index: 8191392 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3236. Min Range: -7.3236
Max Act: 7.0111. Min Act: -0.1700
Data Index: 7699426 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3236. Min Range: -7.3236
Max Act: 7.0111. Min Act: -0.1700
Data Index: 6508087 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3236. Min Range: -7.3236
Max Act: 6.9486. Min Act: -0.1700
Data Index: 1996271 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3236. Min Range: -7.3236
Max Act: 6.9798. Min Act: -0.1700
Data Index: 931856 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3236. Min Range: -7.3236
Max Act: 6.9798. Min Act: -0.1700
Data Index: 7170676 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3236. Min Range: -7.3236
Max Act: 6.9798. Min Act: -0.1700
Data Index: 7596277 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3236. Min Range: -7.3236
Max Act: 6.9173. Min Act: -0.1700
Data Index: 410879 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3236. Min Range: -7.3236
Max Act: 6.8548. Min Act: -0.1700
Data Index: 4360012 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3236. Min Range: -7.3236
Max Act: 6.8236. Min Act: -0.1700
Data Index: 1558327 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3236. Min Range: -7.3236
Max Act: 6.7923. Min Act: -0.1700
Data Index: 8194190 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3236. Min Range: -7.3236
Max Act: 6.8236. Min Act: -0.1700
Data Index: 447067 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3236. Min Range: -7.3236
Max Act: 6.7923. Min Act: -0.1700
Data Index: 1427598 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3236. Min Range: -7.3236
Max Act: 6.7923. Min Act: -0.1700
Data Index: 531913 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3236. Min Range: -7.3236
Max Act: 6.7298. Min Act: -0.1700
Data Index: 2320911 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3236. Min Range: -7.3236
Max Act: 6.7298. Min Act: -0.1700
Data Index: 4159082 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3236. Min Range: -7.3236
Max Act: 6.7298. Min Act: -0.1700
Data Index: 2333228 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3236. Min Range: -7.3236
Max Act: 6.6986. Min Act: -0.1700
Data Index: 4674190 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3236. Min Range: -7.3236
Max Act: 6.6986. Min Act: -0.1700
Data Index: 7777593 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19