Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1103 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5174. Min Range: -2.5174
Max Act: 2.5174. Min Act: -0.1700
Data Index: 2318043 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5174. Min Range: -2.5174
Max Act: 2.4525. Min Act: -0.1700
Data Index: 4923185 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5174. Min Range: -2.5174
Max Act: 2.4200. Min Act: -0.1700
Data Index: 3075801 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5174. Min Range: -2.5174
Max Act: 2.4200. Min Act: -0.1700
Data Index: 3196967 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5174. Min Range: -2.5174
Max Act: 2.4200. Min Act: -0.1700
Data Index: 4923188 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5174. Min Range: -2.5174
Max Act: 2.4200. Min Act: -0.1700
Data Index: 2031789 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5174. Min Range: -2.5174
Max Act: 2.4037. Min Act: -0.1700
Data Index: 7243569 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5174. Min Range: -2.5174
Max Act: 2.4037. Min Act: -0.1700
Data Index: 70128 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5174. Min Range: -2.5174
Max Act: 2.3873. Min Act: -0.1700
Data Index: 3523733 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5174. Min Range: -2.5174
Max Act: 2.3873. Min Act: -0.1700
Data Index: 7076892 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5174. Min Range: -2.5174
Max Act: 2.3873. Min Act: -0.1700
Data Index: 5171174 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5174. Min Range: -2.5174
Max Act: 2.3710. Min Act: -0.1700
Data Index: 1765331 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5174. Min Range: -2.5174
Max Act: 2.3873. Min Act: -0.1700
Data Index: 1313807 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5174. Min Range: -2.5174
Max Act: 2.3873. Min Act: -0.1700
Data Index: 6715421 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5174. Min Range: -2.5174
Max Act: 2.3710. Min Act: -0.1700
Data Index: 3968761 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5174. Min Range: -2.5174
Max Act: 2.3710. Min Act: -0.1700
Data Index: 2901252 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5174. Min Range: -2.5174
Max Act: 2.3710. Min Act: -0.1700
Data Index: 3627079 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5174. Min Range: -2.5174
Max Act: 2.3546. Min Act: -0.1700
Data Index: 3928740 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5174. Min Range: -2.5174
Max Act: 2.3546. Min Act: -0.1700
Data Index: 1781237 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5174. Min Range: -2.5174
Max Act: 2.3546. Min Act: -0.1700
Data Index: 4639941 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19