Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2150 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.3743. Min Range: -10.3743
Max Act: 10.3743. Min Act: -0.1700
Data Index: 3204182 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3743. Min Range: -10.3743
Max Act: 10.2493. Min Act: -0.1700
Data Index: 4184800 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3743. Min Range: -10.3743
Max Act: 9.6243. Min Act: -0.1691
Data Index: 3698617 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3743. Min Range: -10.3743
Max Act: 10.1868. Min Act: -0.1697
Data Index: 893320 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3743. Min Range: -10.3743
Max Act: 9.4368. Min Act: -0.1700
Data Index: 4604992 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3743. Min Range: -10.3743
Max Act: 5.7806. Min Act: -0.1693
Data Index: 171862 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3743. Min Range: -10.3743
Max Act: 7.8118. Min Act: -0.1700
Data Index: 8268932 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3743. Min Range: -10.3743
Max Act: 7.9368. Min Act: -0.1658
Data Index: 1706017 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3743. Min Range: -10.3743
Max Act: 9.6243. Min Act: -0.1700
Data Index: 8576329 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3743. Min Range: -10.3743
Max Act: 8.8743. Min Act: -0.1670
Data Index: 967212 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3743. Min Range: -10.3743
Max Act: 9.1868. Min Act: -0.1699
Data Index: 5148131 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3743. Min Range: -10.3743
Max Act: 7.0306. Min Act: -0.1700
Data Index: 521924 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3743. Min Range: -10.3743
Max Act: 7.4056. Min Act: -0.1700
Data Index: 691007 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3743. Min Range: -10.3743
Max Act: 9.4993. Min Act: -0.1700
Data Index: 2809631 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3743. Min Range: -10.3743
Max Act: 9.3743. Min Act: -0.1699
Data Index: 3577615 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3743. Min Range: -10.3743
Max Act: 7.1556. Min Act: -0.1700
Data Index: 7215647 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3743. Min Range: -10.3743
Max Act: 8.9368. Min Act: -0.1700
Data Index: 8722941 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3743. Min Range: -10.3743
Max Act: 9.0618. Min Act: -0.1691
Data Index: 618973 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3743. Min Range: -10.3743
Max Act: 7.9993. Min Act: -0.1700
Data Index: 6859800 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3743. Min Range: -10.3743
Max Act: 8.7493. Min Act: -0.1700
Data Index: 5736787 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19