Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3104 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7983. Min Range: -5.7983
Max Act: 5.7983. Min Act: -0.1700
Data Index: 5989722 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7983. Min Range: -5.7983
Max Act: 5.7671. Min Act: -0.1700
Data Index: 8145203 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7983. Min Range: -5.7983
Max Act: 5.7046. Min Act: -0.1700
Data Index: 5259124 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7983. Min Range: -5.7983
Max Act: 5.6733. Min Act: -0.1700
Data Index: 7874300 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7983. Min Range: -5.7983
Max Act: 5.6733. Min Act: -0.1700
Data Index: 4505669 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7983. Min Range: -5.7983
Max Act: 5.6421. Min Act: -0.1700
Data Index: 1494363 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7983. Min Range: -5.7983
Max Act: 5.6421. Min Act: -0.1700
Data Index: 5014278 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7983. Min Range: -5.7983
Max Act: 5.5796. Min Act: -0.1700
Data Index: 1494359 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7983. Min Range: -5.7983
Max Act: 5.5171. Min Act: -0.1700
Data Index: 979355 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7983. Min Range: -5.7983
Max Act: 5.5171. Min Act: -0.1700
Data Index: 5912564 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7983. Min Range: -5.7983
Max Act: 5.5171. Min Act: -0.1700
Data Index: 1494365 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7983. Min Range: -5.7983
Max Act: 5.4858. Min Act: -0.1700
Data Index: 6763575 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7983. Min Range: -5.7983
Max Act: 5.4546. Min Act: -0.1700
Data Index: 1620761 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7983. Min Range: -5.7983
Max Act: 5.4858. Min Act: -0.1700
Data Index: 7173349 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7983. Min Range: -5.7983
Max Act: 5.4546. Min Act: -0.1700
Data Index: 2432814 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7983. Min Range: -5.7983
Max Act: 5.4546. Min Act: -0.1700
Data Index: 8101659 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7983. Min Range: -5.7983
Max Act: 5.4233. Min Act: -0.1700
Data Index: 492213 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7983. Min Range: -5.7983
Max Act: 5.4546. Min Act: -0.1700
Data Index: 3169054 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7983. Min Range: -5.7983
Max Act: 5.4233. Min Act: -0.1700
Data Index: 2910620 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7983. Min Range: -5.7983
Max Act: 5.4233. Min Act: -0.1700
Data Index: 557220 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19