Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5377 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1771. Min Range: -3.1771
Max Act: 3.1771. Min Act: -0.1700
Data Index: 1104220 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1771. Min Range: -3.1771
Max Act: 3.1456. Min Act: -0.1700
Data Index: 4618315 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1771. Min Range: -3.1771
Max Act: 3.1299. Min Act: -0.1700
Data Index: 181679 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1771. Min Range: -3.1771
Max Act: 3.0511. Min Act: -0.1700
Data Index: 3444331 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1771. Min Range: -3.1771
Max Act: 3.0511. Min Act: -0.1700
Data Index: 5555811 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1771. Min Range: -3.1771
Max Act: 3.0511. Min Act: -0.1700
Data Index: 1266875 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1771. Min Range: -3.1771
Max Act: 3.0511. Min Act: -0.1700
Data Index: 7915189 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1771. Min Range: -3.1771
Max Act: 3.0511. Min Act: -0.1700
Data Index: 2262106 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1771. Min Range: -3.1771
Max Act: 3.0353. Min Act: -0.1700
Data Index: 1372177 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1771. Min Range: -3.1771
Max Act: 3.0353. Min Act: -0.1700
Data Index: 4053161 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1771. Min Range: -3.1771
Max Act: 3.0353. Min Act: -0.1700
Data Index: 5308427 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1771. Min Range: -3.1771
Max Act: 3.0195. Min Act: -0.1700
Data Index: 4483668 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1771. Min Range: -3.1771
Max Act: 3.0195. Min Act: -0.1700
Data Index: 3229103 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1771. Min Range: -3.1771
Max Act: 3.0195. Min Act: -0.1700
Data Index: 336629 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1771. Min Range: -3.1771
Max Act: 3.0195. Min Act: -0.1700
Data Index: 2015697 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1771. Min Range: -3.1771
Max Act: 3.0195. Min Act: -0.1700
Data Index: 1112109 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1771. Min Range: -3.1771
Max Act: 3.0195. Min Act: -0.1700
Data Index: 465055 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1771. Min Range: -3.1771
Max Act: 3.0037. Min Act: -0.1700
Data Index: 7551402 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1771. Min Range: -3.1771
Max Act: 3.0037. Min Act: -0.1700
Data Index: 2970282 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1771. Min Range: -3.1771
Max Act: 3.0037. Min Act: -0.1700
Data Index: 7609729 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19