Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3037 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8379. Min Range: -5.8379
Max Act: 5.8379. Min Act: -0.1700
Data Index: 910738 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8379. Min Range: -5.8379
Max Act: 5.8379. Min Act: -0.1700
Data Index: 6062520 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8379. Min Range: -5.8379
Max Act: 5.7754. Min Act: -0.1700
Data Index: 40074 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8379. Min Range: -5.8379
Max Act: 5.7441. Min Act: -0.1700
Data Index: 4797089 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8379. Min Range: -5.8379
Max Act: 5.7129. Min Act: -0.1700
Data Index: 1086892 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8379. Min Range: -5.8379
Max Act: 5.7441. Min Act: -0.1700
Data Index: 5929010 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8379. Min Range: -5.8379
Max Act: 5.7129. Min Act: -0.1700
Data Index: 5279278 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8379. Min Range: -5.8379
Max Act: 5.7129. Min Act: -0.1700
Data Index: 937542 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8379. Min Range: -5.8379
Max Act: 5.6816. Min Act: -0.1700
Data Index: 2908006 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8379. Min Range: -5.8379
Max Act: 5.7129. Min Act: -0.1700
Data Index: 8617858 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8379. Min Range: -5.8379
Max Act: 5.6816. Min Act: -0.1700
Data Index: 8431296 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8379. Min Range: -5.8379
Max Act: 5.6504. Min Act: -0.1700
Data Index: 6926322 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8379. Min Range: -5.8379
Max Act: 5.6191. Min Act: -0.1700
Data Index: 6847895 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8379. Min Range: -5.8379
Max Act: 5.5879. Min Act: -0.1700
Data Index: 7618537 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8379. Min Range: -5.8379
Max Act: 5.5879. Min Act: -0.1700
Data Index: 7299657 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8379. Min Range: -5.8379
Max Act: 5.5879. Min Act: -0.1700
Data Index: 1142214 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8379. Min Range: -5.8379
Max Act: 5.5566. Min Act: -0.1700
Data Index: 8345794 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8379. Min Range: -5.8379
Max Act: 5.5566. Min Act: -0.1700
Data Index: 6136355 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8379. Min Range: -5.8379
Max Act: 5.5566. Min Act: -0.1700
Data Index: 3843328 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8379. Min Range: -5.8379
Max Act: 5.5254. Min Act: -0.1700
Data Index: 259864 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19