Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4571 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2991. Min Range: -7.2991
Max Act: 7.2991. Min Act: -0.1700
Data Index: 7767025 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2991. Min Range: -7.2991
Max Act: 6.9866. Min Act: -0.1700
Data Index: 7815892 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2991. Min Range: -7.2991
Max Act: 6.8616. Min Act: -0.1700
Data Index: 2641099 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2991. Min Range: -7.2991
Max Act: 6.8616. Min Act: -0.1700
Data Index: 4776343 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2991. Min Range: -7.2991
Max Act: 6.8616. Min Act: -0.1700
Data Index: 7467502 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2991. Min Range: -7.2991
Max Act: 6.7054. Min Act: -0.1700
Data Index: 2467178 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2991. Min Range: -7.2991
Max Act: 6.6741. Min Act: -0.1700
Data Index: 3250729 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2991. Min Range: -7.2991
Max Act: 6.6429. Min Act: -0.1700
Data Index: 6712415 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2991. Min Range: -7.2991
Max Act: 6.6429. Min Act: -0.1700
Data Index: 8099327 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2991. Min Range: -7.2991
Max Act: 6.6116. Min Act: -0.1700
Data Index: 184857 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2991. Min Range: -7.2991
Max Act: 6.5179. Min Act: -0.1700
Data Index: 1434977 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2991. Min Range: -7.2991
Max Act: 6.5179. Min Act: -0.1700
Data Index: 5973592 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2991. Min Range: -7.2991
Max Act: 6.5179. Min Act: -0.1700
Data Index: 6547823 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2991. Min Range: -7.2991
Max Act: 6.4866. Min Act: -0.1700
Data Index: 1448029 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2991. Min Range: -7.2991
Max Act: 6.5179. Min Act: -0.1700
Data Index: 7039037 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2991. Min Range: -7.2991
Max Act: 6.4554. Min Act: -0.1700
Data Index: 4147904 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2991. Min Range: -7.2991
Max Act: 6.4866. Min Act: -0.1700
Data Index: 4163603 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2991. Min Range: -7.2991
Max Act: 6.4554. Min Act: -0.1700
Data Index: 5268367 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2991. Min Range: -7.2991
Max Act: 6.4241. Min Act: -0.1700
Data Index: 3089939 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2991. Min Range: -7.2991
Max Act: 6.4241. Min Act: -0.1700
Data Index: 2077732 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19