Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 574 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5850. Min Range: -3.5850
Max Act: 3.5850. Min Act: -0.1700
Data Index: 1087984 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5850. Min Range: -3.5850
Max Act: 3.5380. Min Act: -0.1700
Data Index: 2238958 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5850. Min Range: -3.5850
Max Act: 3.5224. Min Act: -0.1700
Data Index: 2704153 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5850. Min Range: -3.5850
Max Act: 3.5067. Min Act: -0.1700
Data Index: 1026406 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5850. Min Range: -3.5850
Max Act: 3.4911. Min Act: -0.1700
Data Index: 8016402 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5850. Min Range: -3.5850
Max Act: 3.5067. Min Act: -0.1700
Data Index: 608483 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5850. Min Range: -3.5850
Max Act: 3.4597. Min Act: -0.1700
Data Index: 7930081 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5850. Min Range: -3.5850
Max Act: 3.4754. Min Act: -0.1700
Data Index: 6229813 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5850. Min Range: -3.5850
Max Act: 3.4754. Min Act: -0.1700
Data Index: 5223889 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5850. Min Range: -3.5850
Max Act: 3.4284. Min Act: -0.1700
Data Index: 6543097 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5850. Min Range: -3.5850
Max Act: 3.4284. Min Act: -0.1700
Data Index: 4397424 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5850. Min Range: -3.5850
Max Act: 3.4441. Min Act: -0.1700
Data Index: 7566077 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5850. Min Range: -3.5850
Max Act: 3.4127. Min Act: -0.1700
Data Index: 6521707 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5850. Min Range: -3.5850
Max Act: 3.4284. Min Act: -0.1700
Data Index: 6956091 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5850. Min Range: -3.5850
Max Act: 3.4284. Min Act: -0.1700
Data Index: 6188800 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5850. Min Range: -3.5850
Max Act: 3.4284. Min Act: -0.1700
Data Index: 825819 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5850. Min Range: -3.5850
Max Act: 3.4127. Min Act: -0.1700
Data Index: 2854497 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5850. Min Range: -3.5850
Max Act: 3.4284. Min Act: -0.1700
Data Index: 1254042 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5850. Min Range: -3.5850
Max Act: 3.4127. Min Act: -0.1700
Data Index: 4737677 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5850. Min Range: -3.5850
Max Act: 3.4441. Min Act: -0.1700
Data Index: 2573751 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19