Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2831 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9241. Min Range: -6.9241
Max Act: 6.9241. Min Act: -0.1700
Data Index: 280488 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9241. Min Range: -6.9241
Max Act: 6.8929. Min Act: -0.1700
Data Index: 2197717 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9241. Min Range: -6.9241
Max Act: 6.8616. Min Act: -0.1700
Data Index: 6536798 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9241. Min Range: -6.9241
Max Act: 6.7991. Min Act: -0.1700
Data Index: 1920478 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9241. Min Range: -6.9241
Max Act: 6.7366. Min Act: -0.1700
Data Index: 5202953 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9241. Min Range: -6.9241
Max Act: 6.7366. Min Act: -0.1700
Data Index: 8763113 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9241. Min Range: -6.9241
Max Act: 6.7054. Min Act: -0.1700
Data Index: 4254447 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9241. Min Range: -6.9241
Max Act: 6.6741. Min Act: -0.1700
Data Index: 8447107 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9241. Min Range: -6.9241
Max Act: 6.6741. Min Act: -0.1700
Data Index: 7726212 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9241. Min Range: -6.9241
Max Act: 6.6429. Min Act: -0.1700
Data Index: 6239934 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9241. Min Range: -6.9241
Max Act: 6.6116. Min Act: -0.1700
Data Index: 8279586 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9241. Min Range: -6.9241
Max Act: 6.5804. Min Act: -0.1700
Data Index: 7917282 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9241. Min Range: -6.9241
Max Act: 6.5491. Min Act: -0.1700
Data Index: 7750358 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9241. Min Range: -6.9241
Max Act: 6.5804. Min Act: -0.1700
Data Index: 1829452 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9241. Min Range: -6.9241
Max Act: 6.5491. Min Act: -0.1700
Data Index: 6577063 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9241. Min Range: -6.9241
Max Act: 6.4866. Min Act: -0.1700
Data Index: 3710706 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9241. Min Range: -6.9241
Max Act: 6.4866. Min Act: -0.1700
Data Index: 253431 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9241. Min Range: -6.9241
Max Act: 6.4866. Min Act: -0.1700
Data Index: 5995444 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9241. Min Range: -6.9241
Max Act: 6.4866. Min Act: -0.1700
Data Index: 2179300 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9241. Min Range: -6.9241
Max Act: 6.4554. Min Act: -0.1700
Data Index: 7167652 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19