Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2520 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9380. Min Range: -5.9380
Max Act: 5.9380. Min Act: -0.1700
Data Index: 5295615 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9380. Min Range: -5.9380
Max Act: 5.9067. Min Act: -0.1700
Data Index: 4068282 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9380. Min Range: -5.9380
Max Act: 5.8442. Min Act: -0.1700
Data Index: 1159263 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9380. Min Range: -5.9380
Max Act: 5.7817. Min Act: -0.1700
Data Index: 5559266 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9380. Min Range: -5.9380
Max Act: 5.7817. Min Act: -0.1700
Data Index: 1478469 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9380. Min Range: -5.9380
Max Act: 5.7192. Min Act: -0.1700
Data Index: 6177888 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9380. Min Range: -5.9380
Max Act: 5.6567. Min Act: -0.1700
Data Index: 6431956 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9380. Min Range: -5.9380
Max Act: 5.6880. Min Act: -0.1700
Data Index: 5363663 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9380. Min Range: -5.9380
Max Act: 5.6880. Min Act: -0.1700
Data Index: 978825 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9380. Min Range: -5.9380
Max Act: 5.6255. Min Act: -0.1700
Data Index: 7740685 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9380. Min Range: -5.9380
Max Act: 5.5942. Min Act: -0.1700
Data Index: 3868989 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9380. Min Range: -5.9380
Max Act: 5.5942. Min Act: -0.1700
Data Index: 2994500 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9380. Min Range: -5.9380
Max Act: 5.5317. Min Act: -0.1700
Data Index: 3948706 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9380. Min Range: -5.9380
Max Act: 5.5317. Min Act: -0.1700
Data Index: 4348696 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9380. Min Range: -5.9380
Max Act: 5.4692. Min Act: -0.1700
Data Index: 7236631 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9380. Min Range: -5.9380
Max Act: 5.5005. Min Act: -0.1700
Data Index: 8008095 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9380. Min Range: -5.9380
Max Act: 5.4692. Min Act: -0.1700
Data Index: 462891 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9380. Min Range: -5.9380
Max Act: 5.4380. Min Act: -0.1700
Data Index: 6914232 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9380. Min Range: -5.9380
Max Act: 5.4692. Min Act: -0.1700
Data Index: 6235410 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9380. Min Range: -5.9380
Max Act: 5.4067. Min Act: -0.1700
Data Index: 5289994 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19