Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2465 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3719. Min Range: -5.3719
Max Act: 5.3719. Min Act: -0.1700
Data Index: 7984075 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3719. Min Range: -5.3719
Max Act: 5.2781. Min Act: -0.1700
Data Index: 6835229 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3719. Min Range: -5.3719
Max Act: 5.3094. Min Act: -0.1700
Data Index: 3435044 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3719. Min Range: -5.3719
Max Act: 5.2156. Min Act: -0.1700
Data Index: 2358570 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3719. Min Range: -5.3719
Max Act: 5.1844. Min Act: -0.1700
Data Index: 5469408 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3719. Min Range: -5.3719
Max Act: 5.0906. Min Act: -0.1700
Data Index: 3192267 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3719. Min Range: -5.3719
Max Act: 5.0594. Min Act: -0.1700
Data Index: 3215185 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3719. Min Range: -5.3719
Max Act: 5.0281. Min Act: -0.1700
Data Index: 5285558 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3719. Min Range: -5.3719
Max Act: 4.9656. Min Act: -0.1700
Data Index: 5101907 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3719. Min Range: -5.3719
Max Act: 4.9344. Min Act: -0.1700
Data Index: 1427676 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3719. Min Range: -5.3719
Max Act: 4.9344. Min Act: -0.1700
Data Index: 2259925 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3719. Min Range: -5.3719
Max Act: 4.9031. Min Act: -0.1700
Data Index: 8808790 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3719. Min Range: -5.3719
Max Act: 4.9031. Min Act: -0.1700
Data Index: 3317671 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3719. Min Range: -5.3719
Max Act: 4.9031. Min Act: -0.1700
Data Index: 902534 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3719. Min Range: -5.3719
Max Act: 4.9031. Min Act: -0.1700
Data Index: 84554 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3719. Min Range: -5.3719
Max Act: 4.9031. Min Act: -0.1700
Data Index: 672773 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3719. Min Range: -5.3719
Max Act: 4.8719. Min Act: -0.1700
Data Index: 6052882 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3719. Min Range: -5.3719
Max Act: 4.8719. Min Act: -0.1700
Data Index: 8776692 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3719. Min Range: -5.3719
Max Act: 4.8719. Min Act: -0.1700
Data Index: 3556083 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3719. Min Range: -5.3719
Max Act: 4.8719. Min Act: -0.1700
Data Index: 6351472 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19