Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1670 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9186. Min Range: -1.9186
Max Act: 1.9186. Min Act: -0.1700
Data Index: 6547972 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9186. Min Range: -1.9186
Max Act: 1.9186. Min Act: -0.1690
Data Index: 5076526 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9186. Min Range: -1.9186
Max Act: 1.9015. Min Act: -0.1700
Data Index: 4306339 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9186. Min Range: -1.9186
Max Act: 1.8845. Min Act: -0.1700
Data Index: 590184 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9186. Min Range: -1.9186
Max Act: 1.8674. Min Act: -0.1700
Data Index: 7154875 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9186. Min Range: -1.9186
Max Act: 1.8674. Min Act: -0.1700
Data Index: 4648739 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9186. Min Range: -1.9186
Max Act: 1.8674. Min Act: -0.1700
Data Index: 1117467 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9186. Min Range: -1.9186
Max Act: 1.8674. Min Act: -0.1700
Data Index: 5323085 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9186. Min Range: -1.9186
Max Act: 1.8503. Min Act: -0.1700
Data Index: 4857249 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9186. Min Range: -1.9186
Max Act: 1.8503. Min Act: -0.1696
Data Index: 1488934 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9186. Min Range: -1.9186
Max Act: 1.8503. Min Act: -0.1698
Data Index: 3296802 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9186. Min Range: -1.9186
Max Act: 1.8503. Min Act: -0.1700
Data Index: 7449045 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9186. Min Range: -1.9186
Max Act: 1.8331. Min Act: -0.1700
Data Index: 3990076 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9186. Min Range: -1.9186
Max Act: 1.8159. Min Act: -0.1700
Data Index: 333896 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9186. Min Range: -1.9186
Max Act: 1.8159. Min Act: -0.1700
Data Index: 4012160 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9186. Min Range: -1.9186
Max Act: 1.8159. Min Act: -0.1700
Data Index: 5058991 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9186. Min Range: -1.9186
Max Act: 1.8159. Min Act: -0.1690
Data Index: 3644859 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9186. Min Range: -1.9186
Max Act: 1.8073. Min Act: -0.1700
Data Index: 3571852 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9186. Min Range: -1.9186
Max Act: 1.8073. Min Act: -0.1700
Data Index: 2730374 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9186. Min Range: -1.9186
Max Act: 1.8073. Min Act: -0.1700
Data Index: 1646069 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19