Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5158 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3179. Min Range: -6.3179
Max Act: 6.3179. Min Act: -0.1700
Data Index: 2873588 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3179. Min Range: -6.3179
Max Act: 6.2866. Min Act: -0.1700
Data Index: 1368700 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3179. Min Range: -6.3179
Max Act: 6.1304. Min Act: -0.1700
Data Index: 3346418 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3179. Min Range: -6.3179
Max Act: 5.9116. Min Act: -0.1700
Data Index: 2614577 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3179. Min Range: -6.3179
Max Act: 5.7866. Min Act: -0.1700
Data Index: 6259117 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3179. Min Range: -6.3179
Max Act: 5.6616. Min Act: -0.1700
Data Index: 1310667 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3179. Min Range: -6.3179
Max Act: 5.6616. Min Act: -0.1700
Data Index: 6625852 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3179. Min Range: -6.3179
Max Act: 5.6304. Min Act: -0.1700
Data Index: 5112596 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3179. Min Range: -6.3179
Max Act: 5.5991. Min Act: -0.1700
Data Index: 8599823 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3179. Min Range: -6.3179
Max Act: 5.5679. Min Act: -0.1700
Data Index: 4635450 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3179. Min Range: -6.3179
Max Act: 5.5679. Min Act: -0.1700
Data Index: 8078301 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3179. Min Range: -6.3179
Max Act: 5.5679. Min Act: -0.1700
Data Index: 4344825 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3179. Min Range: -6.3179
Max Act: 5.5679. Min Act: -0.1700
Data Index: 7204156 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3179. Min Range: -6.3179
Max Act: 5.5366. Min Act: -0.1700
Data Index: 1212986 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3179. Min Range: -6.3179
Max Act: 5.5366. Min Act: -0.1700
Data Index: 5871231 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3179. Min Range: -6.3179
Max Act: 5.5054. Min Act: -0.1700
Data Index: 117327 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3179. Min Range: -6.3179
Max Act: 5.5366. Min Act: -0.1700
Data Index: 2286491 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3179. Min Range: -6.3179
Max Act: 5.5366. Min Act: -0.1700
Data Index: 1039405 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3179. Min Range: -6.3179
Max Act: 5.4741. Min Act: -0.1700
Data Index: 286343 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3179. Min Range: -6.3179
Max Act: 5.4741. Min Act: -0.1700
Data Index: 1257185 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19