Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1794 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2771. Min Range: -6.2771
Max Act: 6.2771. Min Act: -0.1700
Data Index: 6039350 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2771. Min Range: -6.2771
Max Act: 6.1209. Min Act: -0.1700
Data Index: 2200150 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2771. Min Range: -6.2771
Max Act: 6.0271. Min Act: -0.1700
Data Index: 7675296 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2771. Min Range: -6.2771
Max Act: 5.9334. Min Act: -0.1700
Data Index: 7292018 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2771. Min Range: -6.2771
Max Act: 5.8396. Min Act: -0.1700
Data Index: 2076812 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2771. Min Range: -6.2771
Max Act: 5.8709. Min Act: -0.1700
Data Index: 2436260 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2771. Min Range: -6.2771
Max Act: 5.8396. Min Act: -0.1700
Data Index: 7385280 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2771. Min Range: -6.2771
Max Act: 5.8396. Min Act: -0.1700
Data Index: 6660701 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2771. Min Range: -6.2771
Max Act: 5.8084. Min Act: -0.1700
Data Index: 4661885 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2771. Min Range: -6.2771
Max Act: 5.8084. Min Act: -0.1700
Data Index: 1985572 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2771. Min Range: -6.2771
Max Act: 5.8084. Min Act: -0.1700
Data Index: 554431 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2771. Min Range: -6.2771
Max Act: 5.8084. Min Act: -0.1700
Data Index: 1067147 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2771. Min Range: -6.2771
Max Act: 5.8084. Min Act: -0.1700
Data Index: 2419278 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2771. Min Range: -6.2771
Max Act: 5.7771. Min Act: -0.1700
Data Index: 6769691 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2771. Min Range: -6.2771
Max Act: 5.7771. Min Act: -0.1700
Data Index: 7959457 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2771. Min Range: -6.2771
Max Act: 5.7459. Min Act: -0.1700
Data Index: 8706611 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2771. Min Range: -6.2771
Max Act: 5.7459. Min Act: -0.1700
Data Index: 8686932 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2771. Min Range: -6.2771
Max Act: 5.7459. Min Act: -0.1700
Data Index: 323222 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2771. Min Range: -6.2771
Max Act: 5.7146. Min Act: -0.1700
Data Index: 518031 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2771. Min Range: -6.2771
Max Act: 5.6834. Min Act: -0.1700
Data Index: 6691323 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19