Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1350 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4385. Min Range: -4.4385
Max Act: 4.4385. Min Act: -0.1700
Data Index: 5592599 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4385. Min Range: -4.4385
Max Act: 4.3135. Min Act: -0.1700
Data Index: 5873401 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4385. Min Range: -4.4385
Max Act: 4.3135. Min Act: -0.1700
Data Index: 7429472 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4385. Min Range: -4.4385
Max Act: 4.3135. Min Act: -0.1700
Data Index: 4853743 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4385. Min Range: -4.4385
Max Act: 4.3135. Min Act: -0.1700
Data Index: 7228523 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4385. Min Range: -4.4385
Max Act: 4.2822. Min Act: -0.1700
Data Index: 7734795 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4385. Min Range: -4.4385
Max Act: 4.2822. Min Act: -0.1700
Data Index: 801673 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4385. Min Range: -4.4385
Max Act: 4.2197. Min Act: -0.1700
Data Index: 8464287 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4385. Min Range: -4.4385
Max Act: 4.2510. Min Act: -0.1700
Data Index: 8300083 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4385. Min Range: -4.4385
Max Act: 4.2197. Min Act: -0.1700
Data Index: 8231391 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4385. Min Range: -4.4385
Max Act: 4.2510. Min Act: -0.1700
Data Index: 8152883 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4385. Min Range: -4.4385
Max Act: 4.1884. Min Act: -0.1700
Data Index: 5376931 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4385. Min Range: -4.4385
Max Act: 4.1884. Min Act: -0.1700
Data Index: 5869479 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4385. Min Range: -4.4385
Max Act: 4.2197. Min Act: -0.1700
Data Index: 6766117 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4385. Min Range: -4.4385
Max Act: 4.1884. Min Act: -0.1700
Data Index: 5385457 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4385. Min Range: -4.4385
Max Act: 4.1572. Min Act: -0.1700
Data Index: 5506104 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4385. Min Range: -4.4385
Max Act: 4.1572. Min Act: -0.1700
Data Index: 3209308 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4385. Min Range: -4.4385
Max Act: 4.1572. Min Act: -0.1700
Data Index: 3512599 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4385. Min Range: -4.4385
Max Act: 4.1259. Min Act: -0.1700
Data Index: 8730643 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4385. Min Range: -4.4385
Max Act: 4.1259. Min Act: -0.1700
Data Index: 93047 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19