Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4089 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9192. Min Range: -4.9192
Max Act: 4.9192. Min Act: -0.1700
Data Index: 6710185 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9192. Min Range: -4.9192
Max Act: 4.8879. Min Act: -0.1700
Data Index: 4664399 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9192. Min Range: -4.9192
Max Act: 4.8879. Min Act: -0.1700
Data Index: 3548227 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9192. Min Range: -4.9192
Max Act: 4.8567. Min Act: -0.1700
Data Index: 8147871 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9192. Min Range: -4.9192
Max Act: 4.8254. Min Act: -0.1700
Data Index: 6629093 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9192. Min Range: -4.9192
Max Act: 4.8567. Min Act: -0.1700
Data Index: 5419599 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9192. Min Range: -4.9192
Max Act: 4.8567. Min Act: -0.1700
Data Index: 4769638 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9192. Min Range: -4.9192
Max Act: 4.8567. Min Act: -0.1700
Data Index: 4334966 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9192. Min Range: -4.9192
Max Act: 4.8567. Min Act: -0.1700
Data Index: 2315186 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9192. Min Range: -4.9192
Max Act: 4.8254. Min Act: -0.1700
Data Index: 3495432 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9192. Min Range: -4.9192
Max Act: 4.8254. Min Act: -0.1700
Data Index: 3326454 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9192. Min Range: -4.9192
Max Act: 4.7629. Min Act: -0.1700
Data Index: 2574194 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9192. Min Range: -4.9192
Max Act: 4.7942. Min Act: -0.1700
Data Index: 8596738 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9192. Min Range: -4.9192
Max Act: 4.7629. Min Act: -0.1700
Data Index: 1733544 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9192. Min Range: -4.9192
Max Act: 4.7629. Min Act: -0.1700
Data Index: 4173114 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9192. Min Range: -4.9192
Max Act: 4.7629. Min Act: -0.1700
Data Index: 2470672 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9192. Min Range: -4.9192
Max Act: 4.7629. Min Act: -0.1700
Data Index: 1751187 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9192. Min Range: -4.9192
Max Act: 4.7629. Min Act: -0.1700
Data Index: 1578609 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9192. Min Range: -4.9192
Max Act: 4.7629. Min Act: -0.1700
Data Index: 5286869 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9192. Min Range: -4.9192
Max Act: 4.7629. Min Act: -0.1700
Data Index: 3289994 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19