Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2556 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.0548. Min Range: -9.0548
Max Act: 9.0548. Min Act: -0.1700
Data Index: 1307635 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0548. Min Range: -9.0548
Max Act: 8.9923. Min Act: -0.1700
Data Index: 2249218 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0548. Min Range: -9.0548
Max Act: 8.8673. Min Act: -0.1700
Data Index: 8013174 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0548. Min Range: -9.0548
Max Act: 8.7423. Min Act: -0.1700
Data Index: 5300889 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0548. Min Range: -9.0548
Max Act: 8.6173. Min Act: -0.1700
Data Index: 2052615 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0548. Min Range: -9.0548
Max Act: 8.5548. Min Act: -0.1700
Data Index: 7725474 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0548. Min Range: -9.0548
Max Act: 8.6173. Min Act: -0.1700
Data Index: 5039842 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0548. Min Range: -9.0548
Max Act: 8.5548. Min Act: -0.1700
Data Index: 4427127 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0548. Min Range: -9.0548
Max Act: 8.4923. Min Act: -0.1700
Data Index: 3667606 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0548. Min Range: -9.0548
Max Act: 8.4298. Min Act: -0.1700
Data Index: 5605690 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0548. Min Range: -9.0548
Max Act: 8.4923. Min Act: -0.1700
Data Index: 4900901 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0548. Min Range: -9.0548
Max Act: 8.4923. Min Act: -0.1700
Data Index: 6326715 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0548. Min Range: -9.0548
Max Act: 8.4298. Min Act: -0.1700
Data Index: 4784215 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0548. Min Range: -9.0548
Max Act: 8.4298. Min Act: -0.1700
Data Index: 1192687 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0548. Min Range: -9.0548
Max Act: 8.4298. Min Act: -0.1700
Data Index: 7191470 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0548. Min Range: -9.0548
Max Act: 8.4298. Min Act: -0.1700
Data Index: 7701776 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0548. Min Range: -9.0548
Max Act: 8.3673. Min Act: -0.1700
Data Index: 3157439 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0548. Min Range: -9.0548
Max Act: 8.3673. Min Act: -0.1700
Data Index: 6279584 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0548. Min Range: -9.0548
Max Act: 8.3673. Min Act: -0.1700
Data Index: 6549207 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0548. Min Range: -9.0548
Max Act: 8.3673. Min Act: -0.1700
Data Index: 5924645 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19