Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5376 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5406. Min Range: -4.5406
Max Act: 4.5406. Min Act: -0.1700
Data Index: 5157481 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5406. Min Range: -4.5406
Max Act: 4.5093. Min Act: -0.1700
Data Index: 4858701 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5406. Min Range: -4.5406
Max Act: 4.4781. Min Act: -0.1700
Data Index: 6065343 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5406. Min Range: -4.5406
Max Act: 4.4156. Min Act: -0.1700
Data Index: 4556918 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5406. Min Range: -4.5406
Max Act: 4.4156. Min Act: -0.1700
Data Index: 5809404 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5406. Min Range: -4.5406
Max Act: 4.4468. Min Act: -0.1700
Data Index: 7356674 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5406. Min Range: -4.5406
Max Act: 4.3531. Min Act: -0.1700
Data Index: 8704885 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5406. Min Range: -4.5406
Max Act: 4.4156. Min Act: -0.1700
Data Index: 6566666 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5406. Min Range: -4.5406
Max Act: 4.3843. Min Act: -0.1700
Data Index: 729712 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5406. Min Range: -4.5406
Max Act: 4.3531. Min Act: -0.1700
Data Index: 2049957 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5406. Min Range: -4.5406
Max Act: 4.3218. Min Act: -0.1700
Data Index: 1189058 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5406. Min Range: -4.5406
Max Act: 4.3218. Min Act: -0.1700
Data Index: 1081657 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5406. Min Range: -4.5406
Max Act: 4.3218. Min Act: -0.1700
Data Index: 7446740 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5406. Min Range: -4.5406
Max Act: 4.3218. Min Act: -0.1700
Data Index: 7255383 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5406. Min Range: -4.5406
Max Act: 4.3218. Min Act: -0.1700
Data Index: 1006410 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5406. Min Range: -4.5406
Max Act: 4.2906. Min Act: -0.1700
Data Index: 6639328 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5406. Min Range: -4.5406
Max Act: 4.3218. Min Act: -0.1700
Data Index: 7025355 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5406. Min Range: -4.5406
Max Act: 4.2906. Min Act: -0.1700
Data Index: 6046011 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5406. Min Range: -4.5406
Max Act: 4.2281. Min Act: -0.1700
Data Index: 590637 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5406. Min Range: -4.5406
Max Act: 4.2281. Min Act: -0.1700
Data Index: 7200152 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19