Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3914 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9021. Min Range: -2.9021
Max Act: 2.9021. Min Act: -0.1700
Data Index: 149196 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9021. Min Range: -2.9021
Max Act: 2.8863. Min Act: -0.1700
Data Index: 8221556 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9021. Min Range: -2.9021
Max Act: 2.8386. Min Act: -0.1700
Data Index: 1483480 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9021. Min Range: -2.9021
Max Act: 2.8227. Min Act: -0.1700
Data Index: 6534608 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9021. Min Range: -2.9021
Max Act: 2.8068. Min Act: -0.1700
Data Index: 880971 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9021. Min Range: -2.9021
Max Act: 2.7909. Min Act: -0.1700
Data Index: 2669886 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9021. Min Range: -2.9021
Max Act: 2.7909. Min Act: -0.1700
Data Index: 152621 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9021. Min Range: -2.9021
Max Act: 2.7750. Min Act: -0.1700
Data Index: 6392889 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9021. Min Range: -2.9021
Max Act: 2.7590. Min Act: -0.1700
Data Index: 5613269 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9021. Min Range: -2.9021
Max Act: 2.7590. Min Act: -0.1700
Data Index: 8610503 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9021. Min Range: -2.9021
Max Act: 2.7590. Min Act: -0.1700
Data Index: 1106551 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9021. Min Range: -2.9021
Max Act: 2.7431. Min Act: -0.1700
Data Index: 609598 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9021. Min Range: -2.9021
Max Act: 2.7590. Min Act: -0.1700
Data Index: 5243591 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9021. Min Range: -2.9021
Max Act: 2.7431. Min Act: -0.1700
Data Index: 1888602 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9021. Min Range: -2.9021
Max Act: 2.7431. Min Act: -0.1700
Data Index: 2878219 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9021. Min Range: -2.9021
Max Act: 2.7271. Min Act: -0.1700
Data Index: 6420697 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9021. Min Range: -2.9021
Max Act: 2.7271. Min Act: -0.1700
Data Index: 989146 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9021. Min Range: -2.9021
Max Act: 2.7271. Min Act: -0.1700
Data Index: 4037696 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9021. Min Range: -2.9021
Max Act: 2.7111. Min Act: -0.1700
Data Index: 5249589 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9021. Min Range: -2.9021
Max Act: 2.7111. Min Act: -0.1700
Data Index: 5081507 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19