Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1656 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3112. Min Range: -5.3112
Max Act: 5.3112. Min Act: -0.1700
Data Index: 8580644 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3112. Min Range: -5.3112
Max Act: 5.2800. Min Act: -0.1700
Data Index: 2047672 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3112. Min Range: -5.3112
Max Act: 5.2800. Min Act: -0.1700
Data Index: 1856840 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3112. Min Range: -5.3112
Max Act: 5.1550. Min Act: -0.1700
Data Index: 4152396 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3112. Min Range: -5.3112
Max Act: 5.1550. Min Act: -0.1700
Data Index: 4151555 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3112. Min Range: -5.3112
Max Act: 5.1237. Min Act: -0.1700
Data Index: 1000981 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3112. Min Range: -5.3112
Max Act: 5.0925. Min Act: -0.1700
Data Index: 6033814 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3112. Min Range: -5.3112
Max Act: 5.1550. Min Act: -0.1700
Data Index: 934227 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3112. Min Range: -5.3112
Max Act: 5.0925. Min Act: -0.1700
Data Index: 3356316 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3112. Min Range: -5.3112
Max Act: 5.0300. Min Act: -0.1700
Data Index: 5162526 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3112. Min Range: -5.3112
Max Act: 5.0612. Min Act: -0.1700
Data Index: 3437700 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3112. Min Range: -5.3112
Max Act: 5.0612. Min Act: -0.1700
Data Index: 6274567 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3112. Min Range: -5.3112
Max Act: 4.9987. Min Act: -0.1700
Data Index: 6518256 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3112. Min Range: -5.3112
Max Act: 5.0300. Min Act: -0.1700
Data Index: 3761845 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3112. Min Range: -5.3112
Max Act: 4.9987. Min Act: -0.1700
Data Index: 4513280 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3112. Min Range: -5.3112
Max Act: 5.0300. Min Act: -0.1700
Data Index: 2610448 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3112. Min Range: -5.3112
Max Act: 5.0300. Min Act: -0.1700
Data Index: 3655875 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3112. Min Range: -5.3112
Max Act: 5.0300. Min Act: -0.1700
Data Index: 8588037 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3112. Min Range: -5.3112
Max Act: 4.9987. Min Act: -0.1700
Data Index: 2341422 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3112. Min Range: -5.3112
Max Act: 4.9675. Min Act: -0.1700
Data Index: 1276397 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19