Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3289 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7222. Min Range: -7.7222
Max Act: 7.7222. Min Act: -0.1700
Data Index: 2458116 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7222. Min Range: -7.7222
Max Act: 7.6597. Min Act: -0.1697
Data Index: 7218151 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7222. Min Range: -7.7222
Max Act: 7.6285. Min Act: -0.1700
Data Index: 1710838 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7222. Min Range: -7.7222
Max Act: 7.5347. Min Act: -0.1699
Data Index: 4351099 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7222. Min Range: -7.7222
Max Act: 7.4097. Min Act: -0.1700
Data Index: 3102574 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7222. Min Range: -7.7222
Max Act: 7.3785. Min Act: -0.1700
Data Index: 780382 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7222. Min Range: -7.7222
Max Act: 7.2847. Min Act: -0.1700
Data Index: 3724718 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7222. Min Range: -7.7222
Max Act: 7.2535. Min Act: -0.1700
Data Index: 7049969 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7222. Min Range: -7.7222
Max Act: 7.2222. Min Act: -0.1700
Data Index: 6772723 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7222. Min Range: -7.7222
Max Act: 7.1910. Min Act: -0.1700
Data Index: 1747836 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7222. Min Range: -7.7222
Max Act: 7.0972. Min Act: -0.1700
Data Index: 2370136 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7222. Min Range: -7.7222
Max Act: 7.0347. Min Act: -0.1700
Data Index: 7548419 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7222. Min Range: -7.7222
Max Act: 7.0660. Min Act: -0.1700
Data Index: 1710840 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7222. Min Range: -7.7222
Max Act: 7.0035. Min Act: -0.1690
Data Index: 4833277 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7222. Min Range: -7.7222
Max Act: 7.0035. Min Act: -0.1700
Data Index: 3169251 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7222. Min Range: -7.7222
Max Act: 6.9722. Min Act: -0.1700
Data Index: 7218136 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7222. Min Range: -7.7222
Max Act: 6.9722. Min Act: -0.1700
Data Index: 7048580 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7222. Min Range: -7.7222
Max Act: 6.9097. Min Act: -0.1700
Data Index: 1710843 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7222. Min Range: -7.7222
Max Act: 6.9097. Min Act: -0.1700
Data Index: 308521 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7222. Min Range: -7.7222
Max Act: 6.9410. Min Act: -0.1700
Data Index: 5535171 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19