Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3177 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.8951. Min Range: -11.8951
Max Act: 11.8951. Min Act: -0.1700
Data Index: 7766400 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8951. Min Range: -11.8951
Max Act: 11.7076. Min Act: -0.1700
Data Index: 7602196 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8951. Min Range: -11.8951
Max Act: 11.5201. Min Act: -0.1700
Data Index: 5164855 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8951. Min Range: -11.8951
Max Act: 11.2076. Min Act: -0.1700
Data Index: 3615281 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8951. Min Range: -11.8951
Max Act: 11.1451. Min Act: -0.1700
Data Index: 3473795 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8951. Min Range: -11.8951
Max Act: 11.0201. Min Act: -0.1700
Data Index: 5789816 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8951. Min Range: -11.8951
Max Act: 11.0201. Min Act: -0.1700
Data Index: 5510254 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8951. Min Range: -11.8951
Max Act: 10.8951. Min Act: -0.1700
Data Index: 6880204 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8951. Min Range: -11.8951
Max Act: 10.9576. Min Act: -0.1700
Data Index: 7370795 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8951. Min Range: -11.8951
Max Act: 10.9576. Min Act: -0.1700
Data Index: 2137767 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8951. Min Range: -11.8951
Max Act: 10.8951. Min Act: -0.1700
Data Index: 4052352 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8951. Min Range: -11.8951
Max Act: 10.8951. Min Act: -0.1699
Data Index: 424816 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8951. Min Range: -11.8951
Max Act: 10.8951. Min Act: -0.1700
Data Index: 5592773 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8951. Min Range: -11.8951
Max Act: 10.8326. Min Act: -0.1698
Data Index: 6097885 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8951. Min Range: -11.8951
Max Act: 10.7076. Min Act: -0.1700
Data Index: 1944354 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8951. Min Range: -11.8951
Max Act: 10.7701. Min Act: -0.1700
Data Index: 6019088 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8951. Min Range: -11.8951
Max Act: 10.7076. Min Act: -0.1700
Data Index: 4744132 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8951. Min Range: -11.8951
Max Act: 10.6451. Min Act: -0.1700
Data Index: 4961535 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8951. Min Range: -11.8951
Max Act: 10.6451. Min Act: -0.1700
Data Index: 3402884 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8951. Min Range: -11.8951
Max Act: 10.6451. Min Act: -0.1700
Data Index: 6301670 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19