Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3622 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2169. Min Range: -1.2169
Max Act: 1.2169. Min Act: -0.1700
Data Index: 1176125 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2169. Min Range: -1.2169
Max Act: 1.1465. Min Act: -0.1700
Data Index: 6733041 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2169. Min Range: -1.2169
Max Act: 1.1465. Min Act: -0.1700
Data Index: 8540756 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2169. Min Range: -1.2169
Max Act: 1.1465. Min Act: -0.1692
Data Index: 2100845 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2169. Min Range: -1.2169
Max Act: 1.1465. Min Act: -0.1700
Data Index: 7354493 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2169. Min Range: -1.2169
Max Act: 1.1465. Min Act: -0.1699
Data Index: 2461600 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2169. Min Range: -1.2169
Max Act: 1.1465. Min Act: -0.1700
Data Index: 3808649 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2169. Min Range: -1.2169
Max Act: 1.1465. Min Act: -0.1700
Data Index: 6056032 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2169. Min Range: -1.2169
Max Act: 1.1465. Min Act: -0.1700
Data Index: 5522833 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2169. Min Range: -1.2169
Max Act: 1.1465. Min Act: -0.1700
Data Index: 4634418 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2169. Min Range: -1.2169
Max Act: 1.1465. Min Act: -0.1700
Data Index: 4097905 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2169. Min Range: -1.2169
Max Act: 1.1465. Min Act: -0.1700
Data Index: 3929588 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2169. Min Range: -1.2169
Max Act: 1.1202. Min Act: -0.1700
Data Index: 6235817 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2169. Min Range: -1.2169
Max Act: 1.0852. Min Act: -0.1700
Data Index: 1290722 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2169. Min Range: -1.2169
Max Act: 1.0852. Min Act: -0.1700
Data Index: 4141237 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2169. Min Range: -1.2169
Max Act: 1.0764. Min Act: -0.1700
Data Index: 278981 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2169. Min Range: -1.2169
Max Act: 1.0677. Min Act: -0.1700
Data Index: 8525513 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2169. Min Range: -1.2169
Max Act: 1.0764. Min Act: -0.1700
Data Index: 2766231 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2169. Min Range: -1.2169
Max Act: 1.0764. Min Act: -0.1700
Data Index: 2819233 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2169. Min Range: -1.2169
Max Act: 1.0764. Min Act: -0.1700
Data Index: 1232870 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19