Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 45 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0123. Min Range: -8.0123
Max Act: 8.0123. Min Act: -0.1700
Data Index: 1136682 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.4185. Min Act: -0.1700
Data Index: 7097874 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.3873. Min Act: -0.1700
Data Index: 3488062 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.3560. Min Act: -0.1700
Data Index: 2226334 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.3248. Min Act: -0.1700
Data Index: 7330936 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.3248. Min Act: -0.1700
Data Index: 4340351 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.3560. Min Act: -0.1700
Data Index: 8308601 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.2935. Min Act: -0.1700
Data Index: 1674725 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.2935. Min Act: -0.1700
Data Index: 7178324 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.2623. Min Act: -0.1700
Data Index: 3237505 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.2623. Min Act: -0.1700
Data Index: 849969 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.2310. Min Act: -0.1700
Data Index: 1900704 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.1998. Min Act: -0.1700
Data Index: 4578873 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.1998. Min Act: -0.1700
Data Index: 4635000 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.1998. Min Act: -0.1700
Data Index: 8562058 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.1998. Min Act: -0.1700
Data Index: 5270306 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.1998. Min Act: -0.1700
Data Index: 1813405 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.1998. Min Act: -0.1700
Data Index: 467608 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.1998. Min Act: -0.1700
Data Index: 7785552 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.1998. Min Act: -0.1700
Data Index: 1918087 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19