Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6357 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7649. Min Range: -5.7649
Max Act: 5.7649. Min Act: -0.1700
Data Index: 1056064 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7649. Min Range: -5.7649
Max Act: 5.6399. Min Act: -0.1700
Data Index: 3982695 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7649. Min Range: -5.7649
Max Act: 5.6399. Min Act: -0.1700
Data Index: 2929855 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7649. Min Range: -5.7649
Max Act: 5.6399. Min Act: -0.1700
Data Index: 2053532 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7649. Min Range: -5.7649
Max Act: 5.5774. Min Act: -0.1700
Data Index: 8174248 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7649. Min Range: -5.7649
Max Act: 5.6086. Min Act: -0.1700
Data Index: 4638990 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7649. Min Range: -5.7649
Max Act: 5.4836. Min Act: -0.1700
Data Index: 8000597 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7649. Min Range: -5.7649
Max Act: 5.4524. Min Act: -0.1700
Data Index: 8420962 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7649. Min Range: -5.7649
Max Act: 5.4211. Min Act: -0.1700
Data Index: 1543328 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7649. Min Range: -5.7649
Max Act: 5.4211. Min Act: -0.1700
Data Index: 3730725 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7649. Min Range: -5.7649
Max Act: 5.3899. Min Act: -0.1700
Data Index: 7462083 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7649. Min Range: -5.7649
Max Act: 5.3586. Min Act: -0.1700
Data Index: 8115320 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7649. Min Range: -5.7649
Max Act: 5.3274. Min Act: -0.1700
Data Index: 8463506 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7649. Min Range: -5.7649
Max Act: 5.2961. Min Act: -0.1700
Data Index: 8550679 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7649. Min Range: -5.7649
Max Act: 5.2649. Min Act: -0.1700
Data Index: 7160904 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7649. Min Range: -5.7649
Max Act: 5.2649. Min Act: -0.1700
Data Index: 468063 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7649. Min Range: -5.7649
Max Act: 5.2649. Min Act: -0.1700
Data Index: 6272049 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7649. Min Range: -5.7649
Max Act: 5.2336. Min Act: -0.1700
Data Index: 1651531 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7649. Min Range: -5.7649
Max Act: 5.2336. Min Act: -0.1700
Data Index: 5003464 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7649. Min Range: -5.7649
Max Act: 5.2336. Min Act: -0.1700
Data Index: 5061970 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19