Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1763 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4173. Min Range: -9.4173
Max Act: 9.4173. Min Act: -0.1700
Data Index: 7732893 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4173. Min Range: -9.4173
Max Act: 9.2298. Min Act: -0.1700
Data Index: 203264 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4173. Min Range: -9.4173
Max Act: 9.1673. Min Act: -0.1700
Data Index: 2875612 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4173. Min Range: -9.4173
Max Act: 9.1048. Min Act: -0.1700
Data Index: 5665657 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4173. Min Range: -9.4173
Max Act: 9.1048. Min Act: -0.1700
Data Index: 574815 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4173. Min Range: -9.4173
Max Act: 8.9798. Min Act: -0.1700
Data Index: 5357208 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4173. Min Range: -9.4173
Max Act: 9.0423. Min Act: -0.1700
Data Index: 7574942 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4173. Min Range: -9.4173
Max Act: 8.9173. Min Act: -0.1700
Data Index: 8324114 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4173. Min Range: -9.4173
Max Act: 8.9173. Min Act: -0.1700
Data Index: 2162102 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4173. Min Range: -9.4173
Max Act: 8.9173. Min Act: -0.1700
Data Index: 2974636 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4173. Min Range: -9.4173
Max Act: 8.9173. Min Act: -0.1700
Data Index: 765606 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4173. Min Range: -9.4173
Max Act: 8.9173. Min Act: -0.1700
Data Index: 7586079 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4173. Min Range: -9.4173
Max Act: 8.9173. Min Act: -0.1700
Data Index: 4301165 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4173. Min Range: -9.4173
Max Act: 8.8548. Min Act: -0.1700
Data Index: 2657736 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4173. Min Range: -9.4173
Max Act: 8.8548. Min Act: -0.1700
Data Index: 4877759 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4173. Min Range: -9.4173
Max Act: 8.7923. Min Act: -0.1700
Data Index: 1071386 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4173. Min Range: -9.4173
Max Act: 8.7923. Min Act: -0.1700
Data Index: 2756699 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4173. Min Range: -9.4173
Max Act: 8.7298. Min Act: -0.1700
Data Index: 6913891 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4173. Min Range: -9.4173
Max Act: 8.7298. Min Act: -0.1700
Data Index: 5282762 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4173. Min Range: -9.4173
Max Act: 8.7298. Min Act: -0.1700
Data Index: 5465638 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19