Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3229 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3380. Min Range: -5.3380
Max Act: 5.3380. Min Act: -0.1700
Data Index: 1936940 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3380. Min Range: -5.3380
Max Act: 5.3067. Min Act: -0.1700
Data Index: 2789470 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3380. Min Range: -5.3380
Max Act: 5.2442. Min Act: -0.1700
Data Index: 6336924 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3380. Min Range: -5.3380
Max Act: 5.1817. Min Act: -0.1700
Data Index: 3894410 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3380. Min Range: -5.3380
Max Act: 5.1192. Min Act: -0.1700
Data Index: 7419486 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3380. Min Range: -5.3380
Max Act: 5.1192. Min Act: -0.1700
Data Index: 233027 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3380. Min Range: -5.3380
Max Act: 5.1192. Min Act: -0.1700
Data Index: 1246398 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3380. Min Range: -5.3380
Max Act: 5.0880. Min Act: -0.1700
Data Index: 205771 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3380. Min Range: -5.3380
Max Act: 5.0567. Min Act: -0.1700
Data Index: 6509624 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3380. Min Range: -5.3380
Max Act: 5.0255. Min Act: -0.1700
Data Index: 1415955 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3380. Min Range: -5.3380
Max Act: 4.9630. Min Act: -0.1700
Data Index: 5777651 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3380. Min Range: -5.3380
Max Act: 4.9942. Min Act: -0.1700
Data Index: 3788621 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3380. Min Range: -5.3380
Max Act: 4.9942. Min Act: -0.1700
Data Index: 1196534 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3380. Min Range: -5.3380
Max Act: 4.9942. Min Act: -0.1700
Data Index: 484994 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3380. Min Range: -5.3380
Max Act: 4.9942. Min Act: -0.1700
Data Index: 7167293 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3380. Min Range: -5.3380
Max Act: 4.9630. Min Act: -0.1700
Data Index: 2087590 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3380. Min Range: -5.3380
Max Act: 4.9630. Min Act: -0.1700
Data Index: 7868479 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3380. Min Range: -5.3380
Max Act: 4.9942. Min Act: -0.1700
Data Index: 8316469 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3380. Min Range: -5.3380
Max Act: 4.9942. Min Act: -0.1700
Data Index: 8484175 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3380. Min Range: -5.3380
Max Act: 4.9630. Min Act: -0.1700
Data Index: 3035738 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19