Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3045 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8491. Min Range: -5.8491
Max Act: 5.8491. Min Act: -0.1700
Data Index: 3587710 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8491. Min Range: -5.8491
Max Act: 5.8179. Min Act: -0.1700
Data Index: 6848539 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8491. Min Range: -5.8491
Max Act: 5.7866. Min Act: -0.1700
Data Index: 2414407 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8491. Min Range: -5.8491
Max Act: 5.7241. Min Act: -0.1700
Data Index: 1307913 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8491. Min Range: -5.8491
Max Act: 5.6929. Min Act: -0.1700
Data Index: 4860223 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8491. Min Range: -5.8491
Max Act: 5.6929. Min Act: -0.1700
Data Index: 5903423 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8491. Min Range: -5.8491
Max Act: 5.6616. Min Act: -0.1700
Data Index: 358387 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8491. Min Range: -5.8491
Max Act: 5.6616. Min Act: -0.1700
Data Index: 2601968 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8491. Min Range: -5.8491
Max Act: 5.6616. Min Act: -0.1700
Data Index: 2138642 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8491. Min Range: -5.8491
Max Act: 5.6304. Min Act: -0.1700
Data Index: 2032249 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8491. Min Range: -5.8491
Max Act: 5.6304. Min Act: -0.1700
Data Index: 4679535 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8491. Min Range: -5.8491
Max Act: 5.6304. Min Act: -0.1700
Data Index: 2723589 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8491. Min Range: -5.8491
Max Act: 5.5991. Min Act: -0.1700
Data Index: 605725 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8491. Min Range: -5.8491
Max Act: 5.5679. Min Act: -0.1700
Data Index: 424082 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8491. Min Range: -5.8491
Max Act: 5.5679. Min Act: -0.1700
Data Index: 2375192 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8491. Min Range: -5.8491
Max Act: 5.5679. Min Act: -0.1700
Data Index: 7287150 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8491. Min Range: -5.8491
Max Act: 5.5366. Min Act: -0.1700
Data Index: 2068701 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8491. Min Range: -5.8491
Max Act: 5.5054. Min Act: -0.1700
Data Index: 1893930 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8491. Min Range: -5.8491
Max Act: 5.5366. Min Act: -0.1700
Data Index: 7276111 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8491. Min Range: -5.8491
Max Act: 5.5366. Min Act: -0.1700
Data Index: 2634061 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19