Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1805 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5447. Min Range: -4.5447
Max Act: 4.5447. Min Act: -0.1700
Data Index: 2695103 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5447. Min Range: -4.5447
Max Act: 4.4509. Min Act: -0.1700
Data Index: 2751245 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5447. Min Range: -4.5447
Max Act: 4.3884. Min Act: -0.1700
Data Index: 7174370 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5447. Min Range: -4.5447
Max Act: 4.3572. Min Act: -0.1700
Data Index: 6042641 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5447. Min Range: -4.5447
Max Act: 4.3259. Min Act: -0.1700
Data Index: 560026 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5447. Min Range: -4.5447
Max Act: 4.3572. Min Act: -0.1700
Data Index: 546098 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5447. Min Range: -4.5447
Max Act: 4.3259. Min Act: -0.1700
Data Index: 1749047 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5447. Min Range: -4.5447
Max Act: 4.2947. Min Act: -0.1700
Data Index: 4774651 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5447. Min Range: -4.5447
Max Act: 4.3259. Min Act: -0.1700
Data Index: 7324113 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5447. Min Range: -4.5447
Max Act: 4.2947. Min Act: -0.1700
Data Index: 2025095 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5447. Min Range: -4.5447
Max Act: 4.2947. Min Act: -0.1700
Data Index: 2299242 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5447. Min Range: -4.5447
Max Act: 4.2947. Min Act: -0.1700
Data Index: 7768856 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5447. Min Range: -4.5447
Max Act: 4.2634. Min Act: -0.1700
Data Index: 6007427 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5447. Min Range: -4.5447
Max Act: 4.2634. Min Act: -0.1700
Data Index: 5829008 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5447. Min Range: -4.5447
Max Act: 4.2634. Min Act: -0.1700
Data Index: 1203817 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5447. Min Range: -4.5447
Max Act: 4.2322. Min Act: -0.1700
Data Index: 4671664 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5447. Min Range: -4.5447
Max Act: 4.2322. Min Act: -0.1700
Data Index: 1463064 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5447. Min Range: -4.5447
Max Act: 4.2009. Min Act: -0.1700
Data Index: 3004683 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5447. Min Range: -4.5447
Max Act: 4.2009. Min Act: -0.1700
Data Index: 6391936 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5447. Min Range: -4.5447
Max Act: 4.2009. Min Act: -0.1700
Data Index: 3563389 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19