Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1873 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5247. Min Range: -7.5247
Max Act: 7.5247. Min Act: -0.1700
Data Index: 7081648 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5247. Min Range: -7.5247
Max Act: 7.4935. Min Act: -0.1700
Data Index: 6654587 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5247. Min Range: -7.5247
Max Act: 7.4310. Min Act: -0.1700
Data Index: 3034999 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5247. Min Range: -7.5247
Max Act: 7.4310. Min Act: -0.1700
Data Index: 2016365 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5247. Min Range: -7.5247
Max Act: 7.3685. Min Act: -0.1700
Data Index: 7545448 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5247. Min Range: -7.5247
Max Act: 7.3685. Min Act: -0.1700
Data Index: 1132117 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5247. Min Range: -7.5247
Max Act: 7.2747. Min Act: -0.1700
Data Index: 1812256 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5247. Min Range: -7.5247
Max Act: 7.2747. Min Act: -0.1700
Data Index: 2185801 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5247. Min Range: -7.5247
Max Act: 7.2435. Min Act: -0.1700
Data Index: 7068436 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5247. Min Range: -7.5247
Max Act: 7.2435. Min Act: -0.1700
Data Index: 8284251 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5247. Min Range: -7.5247
Max Act: 7.2435. Min Act: -0.1700
Data Index: 2621107 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5247. Min Range: -7.5247
Max Act: 7.2435. Min Act: -0.1700
Data Index: 4879984 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5247. Min Range: -7.5247
Max Act: 7.2122. Min Act: -0.1700
Data Index: 3309380 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5247. Min Range: -7.5247
Max Act: 7.1497. Min Act: -0.1700
Data Index: 2981430 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5247. Min Range: -7.5247
Max Act: 7.1497. Min Act: -0.1700
Data Index: 5672010 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5247. Min Range: -7.5247
Max Act: 7.1185. Min Act: -0.1700
Data Index: 4130088 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5247. Min Range: -7.5247
Max Act: 7.1185. Min Act: -0.1700
Data Index: 993575 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5247. Min Range: -7.5247
Max Act: 7.0872. Min Act: -0.1700
Data Index: 1471526 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5247. Min Range: -7.5247
Max Act: 7.0247. Min Act: -0.1700
Data Index: 3415887 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5247. Min Range: -7.5247
Max Act: 7.0560. Min Act: -0.1700
Data Index: 2700699 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19