Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2322 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5177. Min Range: -8.5177
Max Act: 8.5177. Min Act: -0.1700
Data Index: 6282254 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5177. Min Range: -8.5177
Max Act: 8.0177. Min Act: -0.1700
Data Index: 4293715 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5177. Min Range: -8.5177
Max Act: 7.9864. Min Act: -0.1700
Data Index: 3478534 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5177. Min Range: -8.5177
Max Act: 7.9239. Min Act: -0.1700
Data Index: 8623090 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5177. Min Range: -8.5177
Max Act: 7.8614. Min Act: -0.1700
Data Index: 4263506 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5177. Min Range: -8.5177
Max Act: 7.7989. Min Act: -0.1700
Data Index: 70558 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5177. Min Range: -8.5177
Max Act: 7.7677. Min Act: -0.1700
Data Index: 6265932 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5177. Min Range: -8.5177
Max Act: 7.7052. Min Act: -0.1700
Data Index: 771757 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5177. Min Range: -8.5177
Max Act: 7.7052. Min Act: -0.1700
Data Index: 6610546 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5177. Min Range: -8.5177
Max Act: 7.7364. Min Act: -0.1700
Data Index: 6821048 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5177. Min Range: -8.5177
Max Act: 7.6739. Min Act: -0.1700
Data Index: 4256466 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5177. Min Range: -8.5177
Max Act: 7.6739. Min Act: -0.1700
Data Index: 8732090 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5177. Min Range: -8.5177
Max Act: 7.7052. Min Act: -0.1700
Data Index: 508657 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5177. Min Range: -8.5177
Max Act: 7.6427. Min Act: -0.1700
Data Index: 6633494 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5177. Min Range: -8.5177
Max Act: 7.5802. Min Act: -0.1700
Data Index: 2201812 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5177. Min Range: -8.5177
Max Act: 7.5802. Min Act: -0.1700
Data Index: 2203681 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5177. Min Range: -8.5177
Max Act: 7.5802. Min Act: -0.1700
Data Index: 5629457 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5177. Min Range: -8.5177
Max Act: 7.5802. Min Act: -0.1700
Data Index: 6120847 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5177. Min Range: -8.5177
Max Act: 7.5489. Min Act: -0.1700
Data Index: 2839859 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5177. Min Range: -8.5177
Max Act: 7.5489. Min Act: -0.1700
Data Index: 8194325 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19