Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 186 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9968. Min Range: -7.9968
Max Act: 7.9968. Min Act: -0.1700
Data Index: 4661933 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9968. Min Range: -7.9968
Max Act: 7.6218. Min Act: -0.1700
Data Index: 1611754 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9968. Min Range: -7.9968
Max Act: 7.4968. Min Act: -0.1700
Data Index: 2989083 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9968. Min Range: -7.9968
Max Act: 7.2156. Min Act: -0.1700
Data Index: 7372015 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9968. Min Range: -7.9968
Max Act: 7.2468. Min Act: -0.1700
Data Index: 2841634 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9968. Min Range: -7.9968
Max Act: 7.1531. Min Act: -0.1700
Data Index: 2493191 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9968. Min Range: -7.9968
Max Act: 7.1531. Min Act: -0.1700
Data Index: 8220115 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9968. Min Range: -7.9968
Max Act: 7.0906. Min Act: -0.1700
Data Index: 4871815 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9968. Min Range: -7.9968
Max Act: 6.9656. Min Act: -0.1700
Data Index: 3776202 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9968. Min Range: -7.9968
Max Act: 6.9656. Min Act: -0.1700
Data Index: 3866842 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9968. Min Range: -7.9968
Max Act: 6.9343. Min Act: -0.1700
Data Index: 412509 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9968. Min Range: -7.9968
Max Act: 6.9031. Min Act: -0.1700
Data Index: 5425481 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9968. Min Range: -7.9968
Max Act: 6.8718. Min Act: -0.1700
Data Index: 5847832 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9968. Min Range: -7.9968
Max Act: 6.7781. Min Act: -0.1700
Data Index: 3523494 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9968. Min Range: -7.9968
Max Act: 6.7156. Min Act: -0.1700
Data Index: 550604 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9968. Min Range: -7.9968
Max Act: 6.7156. Min Act: -0.1700
Data Index: 5255615 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9968. Min Range: -7.9968
Max Act: 6.6843. Min Act: -0.1700
Data Index: 5112714 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9968. Min Range: -7.9968
Max Act: 6.6843. Min Act: -0.1700
Data Index: 7949885 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9968. Min Range: -7.9968
Max Act: 6.7156. Min Act: -0.1700
Data Index: 5331686 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9968. Min Range: -7.9968
Max Act: 6.6531. Min Act: -0.1700
Data Index: 6538823 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19