Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4461 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8567. Min Range: -4.8567
Max Act: 4.8567. Min Act: -0.1700
Data Index: 8682675 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8567. Min Range: -4.8567
Max Act: 4.7317. Min Act: -0.1700
Data Index: 6452277 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8567. Min Range: -4.8567
Max Act: 4.7004. Min Act: -0.1700
Data Index: 1041827 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8567. Min Range: -4.8567
Max Act: 4.7004. Min Act: -0.1700
Data Index: 1803787 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8567. Min Range: -4.8567
Max Act: 4.6379. Min Act: -0.1700
Data Index: 7509008 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8567. Min Range: -4.8567
Max Act: 4.5754. Min Act: -0.1700
Data Index: 6346862 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8567. Min Range: -4.8567
Max Act: 4.6067. Min Act: -0.1700
Data Index: 4911987 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8567. Min Range: -4.8567
Max Act: 4.6067. Min Act: -0.1700
Data Index: 7987692 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8567. Min Range: -4.8567
Max Act: 4.6067. Min Act: -0.1700
Data Index: 8589790 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8567. Min Range: -4.8567
Max Act: 4.5754. Min Act: -0.1700
Data Index: 3413692 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8567. Min Range: -4.8567
Max Act: 4.5754. Min Act: -0.1700
Data Index: 7314523 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8567. Min Range: -4.8567
Max Act: 4.5442. Min Act: -0.1700
Data Index: 1351106 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8567. Min Range: -4.8567
Max Act: 4.4817. Min Act: -0.1700
Data Index: 1683741 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8567. Min Range: -4.8567
Max Act: 4.5129. Min Act: -0.1700
Data Index: 8550928 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8567. Min Range: -4.8567
Max Act: 4.5129. Min Act: -0.1700
Data Index: 4139897 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8567. Min Range: -4.8567
Max Act: 4.5129. Min Act: -0.1700
Data Index: 5523982 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8567. Min Range: -4.8567
Max Act: 4.5129. Min Act: -0.1700
Data Index: 5983770 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8567. Min Range: -4.8567
Max Act: 4.5129. Min Act: -0.1700
Data Index: 1701410 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8567. Min Range: -4.8567
Max Act: 4.5129. Min Act: -0.1700
Data Index: 1616046 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8567. Min Range: -4.8567
Max Act: 4.5129. Min Act: -0.1700
Data Index: 4182376 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19