Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3500 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6578. Min Range: -7.6578
Max Act: 7.6578. Min Act: -0.1700
Data Index: 8612087 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6578. Min Range: -7.6578
Max Act: 7.5953. Min Act: -0.1700
Data Index: 8743172 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6578. Min Range: -7.6578
Max Act: 7.4078. Min Act: -0.1700
Data Index: 8260712 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6578. Min Range: -7.6578
Max Act: 7.4391. Min Act: -0.1700
Data Index: 7804973 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6578. Min Range: -7.6578
Max Act: 7.3766. Min Act: -0.1700
Data Index: 14697 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6578. Min Range: -7.6578
Max Act: 7.3766. Min Act: -0.1700
Data Index: 631053 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6578. Min Range: -7.6578
Max Act: 7.3453. Min Act: -0.1700
Data Index: 1540119 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6578. Min Range: -7.6578
Max Act: 7.2203. Min Act: -0.1700
Data Index: 5196342 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6578. Min Range: -7.6578
Max Act: 7.2516. Min Act: -0.1700
Data Index: 7517978 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6578. Min Range: -7.6578
Max Act: 7.1891. Min Act: -0.1700
Data Index: 7757857 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6578. Min Range: -7.6578
Max Act: 7.2203. Min Act: -0.1700
Data Index: 8749598 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6578. Min Range: -7.6578
Max Act: 7.1578. Min Act: -0.1700
Data Index: 8646362 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6578. Min Range: -7.6578
Max Act: 7.1891. Min Act: -0.1700
Data Index: 7319937 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6578. Min Range: -7.6578
Max Act: 7.1266. Min Act: -0.1700
Data Index: 7771734 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6578. Min Range: -7.6578
Max Act: 7.1578. Min Act: -0.1700
Data Index: 2189629 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6578. Min Range: -7.6578
Max Act: 7.1578. Min Act: -0.1700
Data Index: 4059555 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6578. Min Range: -7.6578
Max Act: 7.0953. Min Act: -0.1700
Data Index: 7841397 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6578. Min Range: -7.6578
Max Act: 7.1578. Min Act: -0.1700
Data Index: 7462030 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6578. Min Range: -7.6578
Max Act: 7.0953. Min Act: -0.1700
Data Index: 8630131 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6578. Min Range: -7.6578
Max Act: 7.0953. Min Act: -0.1700
Data Index: 4401297 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19