Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4075 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4985. Min Range: -2.4985
Max Act: 2.4985. Min Act: -0.1700
Data Index: 2362052 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4985. Min Range: -2.4985
Max Act: 2.2862. Min Act: -0.1700
Data Index: 5402977 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4985. Min Range: -2.4985
Max Act: 2.2697. Min Act: -0.1699
Data Index: 5402976 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4985. Min Range: -2.4985
Max Act: 2.2532. Min Act: -0.1699
Data Index: 2362047 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4985. Min Range: -2.4985
Max Act: 2.2532. Min Act: -0.1700
Data Index: 6142701 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4985. Min Range: -2.4985
Max Act: 2.2367. Min Act: -0.1700
Data Index: 6351075 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4985. Min Range: -2.4985
Max Act: 2.2697. Min Act: -0.1700
Data Index: 2419065 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4985. Min Range: -2.4985
Max Act: 2.2532. Min Act: -0.1684
Data Index: 2362051 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4985. Min Range: -2.4985
Max Act: 2.2697. Min Act: -0.1700
Data Index: 8282795 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4985. Min Range: -2.4985
Max Act: 2.2201. Min Act: -0.1700
Data Index: 2362036 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4985. Min Range: -2.4985
Max Act: 2.1869. Min Act: -0.1700
Data Index: 6648395 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4985. Min Range: -2.4985
Max Act: 2.1869. Min Act: -0.1700
Data Index: 1057936 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4985. Min Range: -2.4985
Max Act: 2.2035. Min Act: -0.1700
Data Index: 8335418 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4985. Min Range: -2.4985
Max Act: 2.1869. Min Act: -0.1700
Data Index: 6619766 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4985. Min Range: -2.4985
Max Act: 2.1869. Min Act: -0.1700
Data Index: 2502026 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4985. Min Range: -2.4985
Max Act: 2.1869. Min Act: -0.1699
Data Index: 1558415 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4985. Min Range: -2.4985
Max Act: 2.1869. Min Act: -0.1700
Data Index: 3797677 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4985. Min Range: -2.4985
Max Act: 2.1869. Min Act: -0.1700
Data Index: 3192645 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4985. Min Range: -2.4985
Max Act: 2.1703. Min Act: -0.1677
Data Index: 2020147 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4985. Min Range: -2.4985
Max Act: 2.1537. Min Act: -0.1695
Data Index: 2362035 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19