Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 766 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1348. Min Range: -11.1348
Max Act: 11.1348. Min Act: -0.1700
Data Index: 4360102 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1348. Min Range: -11.1348
Max Act: 11.0098. Min Act: -0.1700
Data Index: 2350451 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1348. Min Range: -11.1348
Max Act: 10.8223. Min Act: -0.1700
Data Index: 3684224 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1348. Min Range: -11.1348
Max Act: 10.8223. Min Act: -0.1700
Data Index: 1322913 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1348. Min Range: -11.1348
Max Act: 10.7598. Min Act: -0.1700
Data Index: 5640021 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1348. Min Range: -11.1348
Max Act: 10.7598. Min Act: -0.1700
Data Index: 2580620 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1348. Min Range: -11.1348
Max Act: 10.6973. Min Act: -0.1700
Data Index: 6151070 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1348. Min Range: -11.1348
Max Act: 10.6973. Min Act: -0.1700
Data Index: 6538756 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1348. Min Range: -11.1348
Max Act: 10.6973. Min Act: -0.1700
Data Index: 2055226 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1348. Min Range: -11.1348
Max Act: 10.5723. Min Act: -0.1700
Data Index: 7373149 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1348. Min Range: -11.1348
Max Act: 10.6348. Min Act: -0.1700
Data Index: 3271927 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1348. Min Range: -11.1348
Max Act: 10.6348. Min Act: -0.1700
Data Index: 4462246 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1348. Min Range: -11.1348
Max Act: 10.6348. Min Act: -0.1700
Data Index: 4119509 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1348. Min Range: -11.1348
Max Act: 10.6973. Min Act: -0.1700
Data Index: 4361032 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1348. Min Range: -11.1348
Max Act: 10.5723. Min Act: -0.1700
Data Index: 1134685 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1348. Min Range: -11.1348
Max Act: 10.5723. Min Act: -0.1700
Data Index: 2341416 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1348. Min Range: -11.1348
Max Act: 10.5723. Min Act: -0.1700
Data Index: 8637510 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1348. Min Range: -11.1348
Max Act: 10.5723. Min Act: -0.1700
Data Index: 7171183 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1348. Min Range: -11.1348
Max Act: 10.5098. Min Act: -0.1700
Data Index: 4091630 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1348. Min Range: -11.1348
Max Act: 10.5098. Min Act: -0.1700
Data Index: 3068425 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19