Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3195 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2053. Min Range: -1.2053
Max Act: 1.2053. Min Act: -0.1700
Data Index: 5518084 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2053. Min Range: -1.2053
Max Act: 1.1349. Min Act: -0.1700
Data Index: 5294591 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2053. Min Range: -1.2053
Max Act: 1.0998. Min Act: -0.1700
Data Index: 5580351 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2053. Min Range: -1.2053
Max Act: 1.1174. Min Act: -0.1699
Data Index: 4439528 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2053. Min Range: -1.2053
Max Act: 1.0823. Min Act: -0.1700
Data Index: 1420157 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2053. Min Range: -1.2053
Max Act: 1.0823. Min Act: -0.1700
Data Index: 7505585 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2053. Min Range: -1.2053
Max Act: 1.0823. Min Act: -0.1700
Data Index: 2443445 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2053. Min Range: -1.2053
Max Act: 1.0823. Min Act: -0.1700
Data Index: 774919 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2053. Min Range: -1.2053
Max Act: 1.0823. Min Act: -0.1700
Data Index: 5492051 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2053. Min Range: -1.2053
Max Act: 1.0649. Min Act: -0.1700
Data Index: 8671100 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2053. Min Range: -1.2053
Max Act: 1.0474. Min Act: -0.1700
Data Index: 1695809 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2053. Min Range: -1.2053
Max Act: 1.0474. Min Act: -0.1700
Data Index: 3555097 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2053. Min Range: -1.2053
Max Act: 1.0126. Min Act: -0.1700
Data Index: 2224651 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2053. Min Range: -1.2053
Max Act: 1.0126. Min Act: -0.1700
Data Index: 2296541 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2053. Min Range: -1.2053
Max Act: 1.0126. Min Act: -0.1700
Data Index: 8664884 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2053. Min Range: -1.2053
Max Act: 1.0300. Min Act: -0.1699
Data Index: 3158688 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2053. Min Range: -1.2053
Max Act: 0.9952. Min Act: -0.1700
Data Index: 4069127 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2053. Min Range: -1.2053
Max Act: 0.9606. Min Act: -0.1697
Data Index: 1612046 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2053. Min Range: -1.2053
Max Act: 0.9779. Min Act: -0.1700
Data Index: 3333588 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2053. Min Range: -1.2053
Max Act: 0.9779. Min Act: -0.1700
Data Index: 1223677 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19