Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5410 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3768. Min Range: -8.3768
Max Act: 8.3768. Min Act: -0.1700
Data Index: 5601174 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3768. Min Range: -8.3768
Max Act: 8.1893. Min Act: -0.1700
Data Index: 3976730 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3768. Min Range: -8.3768
Max Act: 8.0018. Min Act: -0.1700
Data Index: 7758325 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3768. Min Range: -8.3768
Max Act: 7.9393. Min Act: -0.1700
Data Index: 4770905 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3768. Min Range: -8.3768
Max Act: 8.0018. Min Act: -0.1700
Data Index: 1453029 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3768. Min Range: -8.3768
Max Act: 7.8768. Min Act: -0.1700
Data Index: 8533213 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3768. Min Range: -8.3768
Max Act: 7.8768. Min Act: -0.1700
Data Index: 7055272 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3768. Min Range: -8.3768
Max Act: 7.8143. Min Act: -0.1700
Data Index: 6643162 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3768. Min Range: -8.3768
Max Act: 7.7518. Min Act: -0.1700
Data Index: 8522700 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3768. Min Range: -8.3768
Max Act: 7.7518. Min Act: -0.1700
Data Index: 7571985 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3768. Min Range: -8.3768
Max Act: 7.7518. Min Act: -0.1700
Data Index: 854598 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3768. Min Range: -8.3768
Max Act: 7.7518. Min Act: -0.1700
Data Index: 5792805 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3768. Min Range: -8.3768
Max Act: 7.6893. Min Act: -0.1700
Data Index: 1152095 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3768. Min Range: -8.3768
Max Act: 7.6893. Min Act: -0.1700
Data Index: 6033095 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3768. Min Range: -8.3768
Max Act: 7.6893. Min Act: -0.1700
Data Index: 8787046 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3768. Min Range: -8.3768
Max Act: 7.6581. Min Act: -0.1700
Data Index: 3739491 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3768. Min Range: -8.3768
Max Act: 7.5956. Min Act: -0.1700
Data Index: 7055271 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3768. Min Range: -8.3768
Max Act: 7.6268. Min Act: -0.1700
Data Index: 7545099 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3768. Min Range: -8.3768
Max Act: 7.6268. Min Act: -0.1700
Data Index: 5410053 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3768. Min Range: -8.3768
Max Act: 7.6268. Min Act: -0.1700
Data Index: 6361502 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19