Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2870 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8031. Min Range: -6.8031
Max Act: 6.8031. Min Act: -0.1700
Data Index: 1473383 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8031. Min Range: -6.8031
Max Act: 6.5531. Min Act: -0.1700
Data Index: 3016180 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8031. Min Range: -6.8031
Max Act: 6.0218. Min Act: -0.1700
Data Index: 7719094 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8031. Min Range: -6.8031
Max Act: 5.9906. Min Act: -0.1700
Data Index: 15071 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8031. Min Range: -6.8031
Max Act: 5.8968. Min Act: -0.1700
Data Index: 1998288 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8031. Min Range: -6.8031
Max Act: 5.8656. Min Act: -0.1700
Data Index: 1476381 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8031. Min Range: -6.8031
Max Act: 5.8343. Min Act: -0.1700
Data Index: 5341494 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8031. Min Range: -6.8031
Max Act: 5.7718. Min Act: -0.1700
Data Index: 2133131 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8031. Min Range: -6.8031
Max Act: 5.7406. Min Act: -0.1700
Data Index: 280430 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8031. Min Range: -6.8031
Max Act: 5.7406. Min Act: -0.1700
Data Index: 1919148 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8031. Min Range: -6.8031
Max Act: 5.7093. Min Act: -0.1700
Data Index: 2568901 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8031. Min Range: -6.8031
Max Act: 5.6781. Min Act: -0.1700
Data Index: 726874 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8031. Min Range: -6.8031
Max Act: 5.6781. Min Act: -0.1700
Data Index: 4648350 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8031. Min Range: -6.8031
Max Act: 5.6156. Min Act: -0.1700
Data Index: 1319997 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8031. Min Range: -6.8031
Max Act: 5.6156. Min Act: -0.1700
Data Index: 8209025 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8031. Min Range: -6.8031
Max Act: 5.5843. Min Act: -0.1700
Data Index: 775182 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8031. Min Range: -6.8031
Max Act: 5.5843. Min Act: -0.1700
Data Index: 8411787 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8031. Min Range: -6.8031
Max Act: 5.5843. Min Act: -0.1700
Data Index: 4531054 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8031. Min Range: -6.8031
Max Act: 5.5531. Min Act: -0.1700
Data Index: 3194641 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8031. Min Range: -6.8031
Max Act: 5.5531. Min Act: -0.1700
Data Index: 4775675 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19