Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3097 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3340. Min Range: -7.3340
Max Act: 7.3340. Min Act: -0.1700
Data Index: 1985561 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3340. Min Range: -7.3340
Max Act: 7.2715. Min Act: -0.1700
Data Index: 8517262 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3340. Min Range: -7.3340
Max Act: 7.1465. Min Act: -0.1700
Data Index: 2816564 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3340. Min Range: -7.3340
Max Act: 6.9590. Min Act: -0.1700
Data Index: 963648 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3340. Min Range: -7.3340
Max Act: 6.8965. Min Act: -0.1700
Data Index: 1126567 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3340. Min Range: -7.3340
Max Act: 6.8652. Min Act: -0.1700
Data Index: 2990229 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3340. Min Range: -7.3340
Max Act: 6.8027. Min Act: -0.1700
Data Index: 6374815 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3340. Min Range: -7.3340
Max Act: 6.7090. Min Act: -0.1700
Data Index: 193359 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3340. Min Range: -7.3340
Max Act: 6.7090. Min Act: -0.1700
Data Index: 3343859 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3340. Min Range: -7.3340
Max Act: 6.7090. Min Act: -0.1700
Data Index: 2148707 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3340. Min Range: -7.3340
Max Act: 6.6465. Min Act: -0.1700
Data Index: 4053080 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3340. Min Range: -7.3340
Max Act: 6.6777. Min Act: -0.1700
Data Index: 798758 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3340. Min Range: -7.3340
Max Act: 6.6152. Min Act: -0.1700
Data Index: 5124176 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3340. Min Range: -7.3340
Max Act: 6.5840. Min Act: -0.1700
Data Index: 2271942 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3340. Min Range: -7.3340
Max Act: 6.5840. Min Act: -0.1700
Data Index: 2092700 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3340. Min Range: -7.3340
Max Act: 6.5215. Min Act: -0.1700
Data Index: 6227257 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3340. Min Range: -7.3340
Max Act: 6.5527. Min Act: -0.1700
Data Index: 5882241 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3340. Min Range: -7.3340
Max Act: 6.5527. Min Act: -0.1700
Data Index: 7473151 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3340. Min Range: -7.3340
Max Act: 6.5840. Min Act: -0.1700
Data Index: 5320411 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3340. Min Range: -7.3340
Max Act: 6.5527. Min Act: -0.1700
Data Index: 5174207 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19