Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 987 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3511. Min Range: -8.3511
Max Act: 8.3511. Min Act: -0.1700
Data Index: 6255954 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3511. Min Range: -8.3511
Max Act: 8.1636. Min Act: -0.1700
Data Index: 6074890 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3511. Min Range: -8.3511
Max Act: 8.1636. Min Act: -0.1700
Data Index: 3450794 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3511. Min Range: -8.3511
Max Act: 8.1011. Min Act: -0.1700
Data Index: 7062063 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3511. Min Range: -8.3511
Max Act: 8.1636. Min Act: -0.1700
Data Index: 6468535 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3511. Min Range: -8.3511
Max Act: 8.1011. Min Act: -0.1700
Data Index: 4798230 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3511. Min Range: -8.3511
Max Act: 8.0386. Min Act: -0.1700
Data Index: 4442514 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3511. Min Range: -8.3511
Max Act: 8.1011. Min Act: -0.1700
Data Index: 6530395 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3511. Min Range: -8.3511
Max Act: 7.9136. Min Act: -0.1700
Data Index: 6548476 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3511. Min Range: -8.3511
Max Act: 7.9136. Min Act: -0.1700
Data Index: 7837018 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3511. Min Range: -8.3511
Max Act: 7.9136. Min Act: -0.1700
Data Index: 5647214 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3511. Min Range: -8.3511
Max Act: 7.8511. Min Act: -0.1700
Data Index: 8435487 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3511. Min Range: -8.3511
Max Act: 7.8511. Min Act: -0.1700
Data Index: 4453971 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3511. Min Range: -8.3511
Max Act: 7.8511. Min Act: -0.1700
Data Index: 976405 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3511. Min Range: -8.3511
Max Act: 7.8511. Min Act: -0.1700
Data Index: 3509123 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3511. Min Range: -8.3511
Max Act: 7.7886. Min Act: -0.1700
Data Index: 7114830 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3511. Min Range: -8.3511
Max Act: 7.7886. Min Act: -0.1700
Data Index: 7774179 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3511. Min Range: -8.3511
Max Act: 7.8511. Min Act: -0.1700
Data Index: 117220 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3511. Min Range: -8.3511
Max Act: 7.7261. Min Act: -0.1700
Data Index: 6917414 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3511. Min Range: -8.3511
Max Act: 7.7261. Min Act: -0.1700
Data Index: 6870581 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19