Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3085 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6198. Min Range: -8.6198
Max Act: 8.6198. Min Act: -0.1700
Data Index: 4447950 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6198. Min Range: -8.6198
Max Act: 8.3073. Min Act: -0.1700
Data Index: 1994241 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6198. Min Range: -8.6198
Max Act: 8.2448. Min Act: -0.1700
Data Index: 1274075 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6198. Min Range: -8.6198
Max Act: 8.2448. Min Act: -0.1700
Data Index: 7307617 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6198. Min Range: -8.6198
Max Act: 8.1823. Min Act: -0.1700
Data Index: 711932 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6198. Min Range: -8.6198
Max Act: 8.1198. Min Act: -0.1700
Data Index: 4428839 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6198. Min Range: -8.6198
Max Act: 8.0573. Min Act: -0.1700
Data Index: 4708912 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6198. Min Range: -8.6198
Max Act: 8.0573. Min Act: -0.1700
Data Index: 4313190 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6198. Min Range: -8.6198
Max Act: 7.9948. Min Act: -0.1700
Data Index: 4007707 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6198. Min Range: -8.6198
Max Act: 7.9948. Min Act: -0.1700
Data Index: 8756731 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6198. Min Range: -8.6198
Max Act: 7.9323. Min Act: -0.1700
Data Index: 6159708 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6198. Min Range: -8.6198
Max Act: 7.9948. Min Act: -0.1700
Data Index: 3768716 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6198. Min Range: -8.6198
Max Act: 7.9323. Min Act: -0.1700
Data Index: 7079154 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6198. Min Range: -8.6198
Max Act: 7.9323. Min Act: -0.1700
Data Index: 6894680 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6198. Min Range: -8.6198
Max Act: 7.9323. Min Act: -0.1700
Data Index: 7057421 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6198. Min Range: -8.6198
Max Act: 7.8073. Min Act: -0.1700
Data Index: 3558075 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6198. Min Range: -8.6198
Max Act: 7.8698. Min Act: -0.1700
Data Index: 5399025 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6198. Min Range: -8.6198
Max Act: 7.8698. Min Act: -0.1700
Data Index: 4298169 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6198. Min Range: -8.6198
Max Act: 7.8698. Min Act: -0.1700
Data Index: 7331858 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6198. Min Range: -8.6198
Max Act: 7.8698. Min Act: -0.1700
Data Index: 8191994 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19