Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 787 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.6067. Min Act: -0.1700
Data Index: 6880495 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.6067. Min Act: -0.1700
Data Index: 3028011 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.5754. Min Act: -0.1700
Data Index: 459885 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.5442. Min Act: -0.1700
Data Index: 6880493 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.4817. Min Act: -0.1700
Data Index: 8466450 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.4504. Min Act: -0.1700
Data Index: 2447895 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.4504. Min Act: -0.1700
Data Index: 3868283 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.4504. Min Act: -0.1700
Data Index: 2609399 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.4504. Min Act: -0.1700
Data Index: 1252846 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.4192. Min Act: -0.1700
Data Index: 6701356 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.4192. Min Act: -0.1700
Data Index: 5556017 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.3879. Min Act: -0.1700
Data Index: 3903461 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.3879. Min Act: -0.1700
Data Index: 6945387 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.3879. Min Act: -0.1700
Data Index: 6599621 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.3879. Min Act: -0.1700
Data Index: 7668161 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.3879. Min Act: -0.1700
Data Index: 2671524 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.3879. Min Act: -0.1700
Data Index: 3925488 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.3879. Min Act: -0.1700
Data Index: 8463928 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.3879. Min Act: -0.1700
Data Index: 4367801 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6067. Min Range: -5.6067
Max Act: 5.3879. Min Act: -0.1700
Data Index: 5554248 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19