Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2300 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9554. Min Range: -6.9554
Max Act: 6.9554. Min Act: -0.1700
Data Index: 2529697 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9554. Min Range: -6.9554
Max Act: 6.9241. Min Act: -0.1700
Data Index: 6621474 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9554. Min Range: -6.9554
Max Act: 6.7366. Min Act: -0.1700
Data Index: 2048321 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9554. Min Range: -6.9554
Max Act: 6.7366. Min Act: -0.1700
Data Index: 4398577 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9554. Min Range: -6.9554
Max Act: 6.7366. Min Act: -0.1700
Data Index: 5460005 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9554. Min Range: -6.9554
Max Act: 6.6116. Min Act: -0.1700
Data Index: 5953440 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9554. Min Range: -6.9554
Max Act: 6.5179. Min Act: -0.1700
Data Index: 3029792 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9554. Min Range: -6.9554
Max Act: 6.5179. Min Act: -0.1700
Data Index: 8515610 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9554. Min Range: -6.9554
Max Act: 6.4866. Min Act: -0.1700
Data Index: 8462069 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9554. Min Range: -6.9554
Max Act: 6.5179. Min Act: -0.1700
Data Index: 7426966 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9554. Min Range: -6.9554
Max Act: 6.4241. Min Act: -0.1700
Data Index: 5923686 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9554. Min Range: -6.9554
Max Act: 6.4241. Min Act: -0.1700
Data Index: 1037727 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9554. Min Range: -6.9554
Max Act: 6.4241. Min Act: -0.1700
Data Index: 8775805 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9554. Min Range: -6.9554
Max Act: 6.3929. Min Act: -0.1700
Data Index: 3512986 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9554. Min Range: -6.9554
Max Act: 6.3929. Min Act: -0.1700
Data Index: 2087081 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9554. Min Range: -6.9554
Max Act: 6.3929. Min Act: -0.1700
Data Index: 8314623 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9554. Min Range: -6.9554
Max Act: 6.3616. Min Act: -0.1700
Data Index: 758915 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9554. Min Range: -6.9554
Max Act: 6.2991. Min Act: -0.1700
Data Index: 3233463 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9554. Min Range: -6.9554
Max Act: 6.2679. Min Act: -0.1700
Data Index: 8627126 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9554. Min Range: -6.9554
Max Act: 6.2991. Min Act: -0.1700
Data Index: 3761927 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19