Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2595 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7843. Min Range: -8.7843
Max Act: 8.7843. Min Act: -0.1700
Data Index: 8678955 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7843. Min Range: -8.7843
Max Act: 8.7218. Min Act: -0.1700
Data Index: 1964280 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7843. Min Range: -8.7843
Max Act: 8.5343. Min Act: -0.1700
Data Index: 1136081 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7843. Min Range: -8.7843
Max Act: 8.4718. Min Act: -0.1700
Data Index: 8758788 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7843. Min Range: -8.7843
Max Act: 8.4718. Min Act: -0.1700
Data Index: 6608647 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7843. Min Range: -8.7843
Max Act: 8.4093. Min Act: -0.1700
Data Index: 6105941 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7843. Min Range: -8.7843
Max Act: 8.3468. Min Act: -0.1700
Data Index: 3582863 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7843. Min Range: -8.7843
Max Act: 8.3468. Min Act: -0.1700
Data Index: 5745448 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7843. Min Range: -8.7843
Max Act: 8.3468. Min Act: -0.1700
Data Index: 3757516 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7843. Min Range: -8.7843
Max Act: 8.2843. Min Act: -0.1700
Data Index: 1885610 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7843. Min Range: -8.7843
Max Act: 8.2843. Min Act: -0.1700
Data Index: 1956465 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7843. Min Range: -8.7843
Max Act: 8.3468. Min Act: -0.1700
Data Index: 1923093 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7843. Min Range: -8.7843
Max Act: 8.2218. Min Act: -0.1700
Data Index: 3052460 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7843. Min Range: -8.7843
Max Act: 8.2218. Min Act: -0.1700
Data Index: 6763953 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7843. Min Range: -8.7843
Max Act: 8.2218. Min Act: -0.1700
Data Index: 148974 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7843. Min Range: -8.7843
Max Act: 8.1593. Min Act: -0.1700
Data Index: 4908608 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7843. Min Range: -8.7843
Max Act: 8.1593. Min Act: -0.1700
Data Index: 4302201 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7843. Min Range: -8.7843
Max Act: 8.1593. Min Act: -0.1700
Data Index: 3863577 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7843. Min Range: -8.7843
Max Act: 8.2218. Min Act: -0.1700
Data Index: 5576844 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7843. Min Range: -8.7843
Max Act: 8.1593. Min Act: -0.1700
Data Index: 2523942 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19