Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3693 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2744. Min Range: -6.2744
Max Act: 6.2744. Min Act: -0.1700
Data Index: 6310580 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2744. Min Range: -6.2744
Max Act: 6.1494. Min Act: -0.1700
Data Index: 7854704 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2744. Min Range: -6.2744
Max Act: 6.1181. Min Act: -0.1700
Data Index: 8144159 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2744. Min Range: -6.2744
Max Act: 6.0556. Min Act: -0.1700
Data Index: 3032543 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2744. Min Range: -6.2744
Max Act: 6.0556. Min Act: -0.1700
Data Index: 5131712 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2744. Min Range: -6.2744
Max Act: 6.0244. Min Act: -0.1700
Data Index: 4778280 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2744. Min Range: -6.2744
Max Act: 6.0244. Min Act: -0.1700
Data Index: 1497749 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2744. Min Range: -6.2744
Max Act: 5.9619. Min Act: -0.1700
Data Index: 7680182 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2744. Min Range: -6.2744
Max Act: 5.8681. Min Act: -0.1700
Data Index: 4352732 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2744. Min Range: -6.2744
Max Act: 5.8369. Min Act: -0.1700
Data Index: 2505192 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2744. Min Range: -6.2744
Max Act: 5.7744. Min Act: -0.1700
Data Index: 2522409 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2744. Min Range: -6.2744
Max Act: 5.7744. Min Act: -0.1700
Data Index: 2936934 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2744. Min Range: -6.2744
Max Act: 5.7744. Min Act: -0.1700
Data Index: 6354824 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2744. Min Range: -6.2744
Max Act: 5.7431. Min Act: -0.1700
Data Index: 5886445 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2744. Min Range: -6.2744
Max Act: 5.7431. Min Act: -0.1700
Data Index: 2304691 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2744. Min Range: -6.2744
Max Act: 5.7431. Min Act: -0.1700
Data Index: 89014 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2744. Min Range: -6.2744
Max Act: 5.7431. Min Act: -0.1700
Data Index: 7292980 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2744. Min Range: -6.2744
Max Act: 5.6806. Min Act: -0.1700
Data Index: 1717486 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2744. Min Range: -6.2744
Max Act: 5.7119. Min Act: -0.1700
Data Index: 1990432 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2744. Min Range: -6.2744
Max Act: 5.7119. Min Act: -0.1700
Data Index: 1589036 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19