Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7807. Min Range: -6.7807
Max Act: 6.7807. Min Act: -0.1700
Data Index: 387069 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7807. Min Range: -6.7807
Max Act: 6.4682. Min Act: -0.1700
Data Index: 83900 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7807. Min Range: -6.7807
Max Act: 6.4370. Min Act: -0.1700
Data Index: 5730625 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7807. Min Range: -6.7807
Max Act: 6.4370. Min Act: -0.1700
Data Index: 8167660 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7807. Min Range: -6.7807
Max Act: 6.4370. Min Act: -0.1700
Data Index: 57588 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7807. Min Range: -6.7807
Max Act: 6.3745. Min Act: -0.1700
Data Index: 3364370 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7807. Min Range: -6.7807
Max Act: 6.2807. Min Act: -0.1700
Data Index: 995747 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7807. Min Range: -6.7807
Max Act: 6.2807. Min Act: -0.1700
Data Index: 448020 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7807. Min Range: -6.7807
Max Act: 6.3120. Min Act: -0.1700
Data Index: 3056485 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7807. Min Range: -6.7807
Max Act: 6.2495. Min Act: -0.1700
Data Index: 6205678 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7807. Min Range: -6.7807
Max Act: 6.2182. Min Act: -0.1700
Data Index: 4612102 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7807. Min Range: -6.7807
Max Act: 6.2182. Min Act: -0.1700
Data Index: 6086927 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7807. Min Range: -6.7807
Max Act: 6.1870. Min Act: -0.1700
Data Index: 3432095 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7807. Min Range: -6.7807
Max Act: 6.1870. Min Act: -0.1700
Data Index: 6486072 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7807. Min Range: -6.7807
Max Act: 6.1557. Min Act: -0.1700
Data Index: 4639839 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7807. Min Range: -6.7807
Max Act: 6.1557. Min Act: -0.1700
Data Index: 5358320 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7807. Min Range: -6.7807
Max Act: 6.1557. Min Act: -0.1700
Data Index: 8539635 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7807. Min Range: -6.7807
Max Act: 6.1245. Min Act: -0.1700
Data Index: 8042458 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7807. Min Range: -6.7807
Max Act: 6.1245. Min Act: -0.1700
Data Index: 3415535 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7807. Min Range: -6.7807
Max Act: 6.0932. Min Act: -0.1700
Data Index: 23232 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19