Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1087 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2868. Min Range: -6.2868
Max Act: 6.2868. Min Act: -0.1700
Data Index: 6151901 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2868. Min Range: -6.2868
Max Act: 6.0993. Min Act: -0.1700
Data Index: 2273181 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2868. Min Range: -6.2868
Max Act: 6.0681. Min Act: -0.1700
Data Index: 4144527 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2868. Min Range: -6.2868
Max Act: 5.8181. Min Act: -0.1700
Data Index: 8257664 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2868. Min Range: -6.2868
Max Act: 5.8806. Min Act: -0.1700
Data Index: 1077908 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2868. Min Range: -6.2868
Max Act: 5.8493. Min Act: -0.1700
Data Index: 7828177 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2868. Min Range: -6.2868
Max Act: 5.8181. Min Act: -0.1700
Data Index: 3786244 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2868. Min Range: -6.2868
Max Act: 5.7868. Min Act: -0.1700
Data Index: 1172305 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2868. Min Range: -6.2868
Max Act: 5.7556. Min Act: -0.1700
Data Index: 7117175 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2868. Min Range: -6.2868
Max Act: 5.6931. Min Act: -0.1700
Data Index: 5821426 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2868. Min Range: -6.2868
Max Act: 5.7243. Min Act: -0.1700
Data Index: 444018 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2868. Min Range: -6.2868
Max Act: 5.7556. Min Act: -0.1700
Data Index: 145866 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2868. Min Range: -6.2868
Max Act: 5.6931. Min Act: -0.1700
Data Index: 4945045 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2868. Min Range: -6.2868
Max Act: 5.6931. Min Act: -0.1700
Data Index: 667737 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2868. Min Range: -6.2868
Max Act: 5.6931. Min Act: -0.1700
Data Index: 803937 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2868. Min Range: -6.2868
Max Act: 5.6618. Min Act: -0.1700
Data Index: 710548 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2868. Min Range: -6.2868
Max Act: 5.6618. Min Act: -0.1700
Data Index: 1661626 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2868. Min Range: -6.2868
Max Act: 5.6618. Min Act: -0.1700
Data Index: 1883307 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2868. Min Range: -6.2868
Max Act: 5.6931. Min Act: -0.1700
Data Index: 6714409 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2868. Min Range: -6.2868
Max Act: 5.5993. Min Act: -0.1700
Data Index: 287192 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19