Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3807 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6428. Min Range: -4.6428
Max Act: 4.6428. Min Act: -0.1700
Data Index: 6199353 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6428. Min Range: -4.6428
Max Act: 4.5803. Min Act: -0.1700
Data Index: 4420270 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6428. Min Range: -4.6428
Max Act: 4.5490. Min Act: -0.1699
Data Index: 7552838 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6428. Min Range: -4.6428
Max Act: 4.5490. Min Act: -0.1700
Data Index: 7450049 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6428. Min Range: -4.6428
Max Act: 4.5178. Min Act: -0.1700
Data Index: 2556599 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6428. Min Range: -4.6428
Max Act: 4.5178. Min Act: -0.1700
Data Index: 523982 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6428. Min Range: -4.6428
Max Act: 4.4865. Min Act: -0.1700
Data Index: 3657782 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6428. Min Range: -4.6428
Max Act: 4.4865. Min Act: -0.1700
Data Index: 4088004 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6428. Min Range: -4.6428
Max Act: 4.4553. Min Act: -0.1700
Data Index: 1015332 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6428. Min Range: -4.6428
Max Act: 4.4553. Min Act: -0.1700
Data Index: 6138009 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6428. Min Range: -4.6428
Max Act: 4.4240. Min Act: -0.1700
Data Index: 1753827 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6428. Min Range: -4.6428
Max Act: 4.4240. Min Act: -0.1700
Data Index: 7558845 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6428. Min Range: -4.6428
Max Act: 4.4240. Min Act: -0.1700
Data Index: 938716 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6428. Min Range: -4.6428
Max Act: 4.4240. Min Act: -0.1700
Data Index: 7053745 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6428. Min Range: -4.6428
Max Act: 4.3928. Min Act: -0.1700
Data Index: 1479298 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6428. Min Range: -4.6428
Max Act: 4.3928. Min Act: -0.1700
Data Index: 5814303 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6428. Min Range: -4.6428
Max Act: 4.3928. Min Act: -0.1700
Data Index: 5697716 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6428. Min Range: -4.6428
Max Act: 4.3928. Min Act: -0.1699
Data Index: 711256 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6428. Min Range: -4.6428
Max Act: 4.3928. Min Act: -0.1700
Data Index: 5134314 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6428. Min Range: -4.6428
Max Act: 4.3928. Min Act: -0.1700
Data Index: 5312949 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19