Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 579 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2860. Min Range: -6.2860
Max Act: 6.2860. Min Act: -0.1700
Data Index: 4114718 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2860. Min Range: -6.2860
Max Act: 5.8798. Min Act: -0.1700
Data Index: 4004686 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2860. Min Range: -6.2860
Max Act: 5.9110. Min Act: -0.1700
Data Index: 8398223 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2860. Min Range: -6.2860
Max Act: 5.8485. Min Act: -0.1700
Data Index: 4906664 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2860. Min Range: -6.2860
Max Act: 5.8173. Min Act: -0.1700
Data Index: 1633170 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2860. Min Range: -6.2860
Max Act: 5.8173. Min Act: -0.1700
Data Index: 1987847 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2860. Min Range: -6.2860
Max Act: 5.8173. Min Act: -0.1700
Data Index: 3068506 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2860. Min Range: -6.2860
Max Act: 5.8173. Min Act: -0.1700
Data Index: 3665297 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2860. Min Range: -6.2860
Max Act: 5.7548. Min Act: -0.1700
Data Index: 1505939 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2860. Min Range: -6.2860
Max Act: 5.7860. Min Act: -0.1700
Data Index: 7129488 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2860. Min Range: -6.2860
Max Act: 5.7860. Min Act: -0.1700
Data Index: 1075151 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2860. Min Range: -6.2860
Max Act: 5.7235. Min Act: -0.1700
Data Index: 4973990 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2860. Min Range: -6.2860
Max Act: 5.7860. Min Act: -0.1700
Data Index: 4915305 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2860. Min Range: -6.2860
Max Act: 5.7548. Min Act: -0.1700
Data Index: 2851972 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2860. Min Range: -6.2860
Max Act: 5.7235. Min Act: -0.1700
Data Index: 3477007 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2860. Min Range: -6.2860
Max Act: 5.6923. Min Act: -0.1700
Data Index: 5546785 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2860. Min Range: -6.2860
Max Act: 5.7235. Min Act: -0.1700
Data Index: 838455 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2860. Min Range: -6.2860
Max Act: 5.7548. Min Act: -0.1700
Data Index: 493124 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2860. Min Range: -6.2860
Max Act: 5.7235. Min Act: -0.1700
Data Index: 6103215 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2860. Min Range: -6.2860
Max Act: 5.6610. Min Act: -0.1700
Data Index: 164029 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19