Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3394 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3563. Min Range: -7.3563
Max Act: 7.3563. Min Act: -0.1700
Data Index: 6193815 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3563. Min Range: -7.3563
Max Act: 7.1688. Min Act: -0.1700
Data Index: 881830 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3563. Min Range: -7.3563
Max Act: 7.0751. Min Act: -0.1700
Data Index: 6813516 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3563. Min Range: -7.3563
Max Act: 7.0126. Min Act: -0.1700
Data Index: 1763355 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3563. Min Range: -7.3563
Max Act: 7.0126. Min Act: -0.1700
Data Index: 6795494 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3563. Min Range: -7.3563
Max Act: 6.9813. Min Act: -0.1700
Data Index: 3060194 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3563. Min Range: -7.3563
Max Act: 6.9813. Min Act: -0.1700
Data Index: 5116806 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3563. Min Range: -7.3563
Max Act: 6.9813. Min Act: -0.1700
Data Index: 5192975 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3563. Min Range: -7.3563
Max Act: 6.9813. Min Act: -0.1700
Data Index: 3886320 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3563. Min Range: -7.3563
Max Act: 6.9501. Min Act: -0.1700
Data Index: 5542535 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3563. Min Range: -7.3563
Max Act: 6.9501. Min Act: -0.1700
Data Index: 3993671 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3563. Min Range: -7.3563
Max Act: 6.9813. Min Act: -0.1700
Data Index: 1033745 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3563. Min Range: -7.3563
Max Act: 6.9188. Min Act: -0.1700
Data Index: 6068196 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3563. Min Range: -7.3563
Max Act: 6.9188. Min Act: -0.1700
Data Index: 3988636 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3563. Min Range: -7.3563
Max Act: 6.8876. Min Act: -0.1700
Data Index: 159074 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3563. Min Range: -7.3563
Max Act: 6.9188. Min Act: -0.1700
Data Index: 3900590 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3563. Min Range: -7.3563
Max Act: 6.8876. Min Act: -0.1700
Data Index: 2001300 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3563. Min Range: -7.3563
Max Act: 6.8876. Min Act: -0.1700
Data Index: 7331966 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3563. Min Range: -7.3563
Max Act: 6.8876. Min Act: -0.1700
Data Index: 5135737 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3563. Min Range: -7.3563
Max Act: 6.8563. Min Act: -0.1700
Data Index: 1249820 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19