Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3086 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4790. Min Range: -5.4790
Max Act: 5.4790. Min Act: -0.1700
Data Index: 438845 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4790. Min Range: -5.4790
Max Act: 5.4165. Min Act: -0.1700
Data Index: 171787 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4790. Min Range: -5.4790
Max Act: 5.1665. Min Act: -0.1700
Data Index: 4599099 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4790. Min Range: -5.4790
Max Act: 5.1665. Min Act: -0.1700
Data Index: 2044068 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4790. Min Range: -5.4790
Max Act: 5.1040. Min Act: -0.1700
Data Index: 5375539 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4790. Min Range: -5.4790
Max Act: 5.0727. Min Act: -0.1700
Data Index: 7765213 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4790. Min Range: -5.4790
Max Act: 5.0727. Min Act: -0.1700
Data Index: 3610907 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4790. Min Range: -5.4790
Max Act: 5.0102. Min Act: -0.1700
Data Index: 5107807 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4790. Min Range: -5.4790
Max Act: 5.0102. Min Act: -0.1700
Data Index: 5574338 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4790. Min Range: -5.4790
Max Act: 5.0102. Min Act: -0.1700
Data Index: 2368464 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4790. Min Range: -5.4790
Max Act: 4.9790. Min Act: -0.1700
Data Index: 4432290 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4790. Min Range: -5.4790
Max Act: 4.9477. Min Act: -0.1700
Data Index: 8263978 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4790. Min Range: -5.4790
Max Act: 4.9477. Min Act: -0.1700
Data Index: 929494 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4790. Min Range: -5.4790
Max Act: 4.9477. Min Act: -0.1700
Data Index: 6711869 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4790. Min Range: -5.4790
Max Act: 4.8852. Min Act: -0.1700
Data Index: 1410753 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4790. Min Range: -5.4790
Max Act: 4.9165. Min Act: -0.1700
Data Index: 8069453 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4790. Min Range: -5.4790
Max Act: 4.9165. Min Act: -0.1700
Data Index: 7106489 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4790. Min Range: -5.4790
Max Act: 4.8852. Min Act: -0.1700
Data Index: 4490649 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4790. Min Range: -5.4790
Max Act: 4.8540. Min Act: -0.1700
Data Index: 5845793 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4790. Min Range: -5.4790
Max Act: 4.8852. Min Act: -0.1700
Data Index: 2381255 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19