Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1428 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3110. Min Range: -4.3110
Max Act: 4.3110. Min Act: -0.1700
Data Index: 6432813 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3110. Min Range: -4.3110
Max Act: 4.2798. Min Act: -0.1700
Data Index: 8620735 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3110. Min Range: -4.3110
Max Act: 4.0923. Min Act: -0.1700
Data Index: 8670002 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3110. Min Range: -4.3110
Max Act: 4.0610. Min Act: -0.1700
Data Index: 1562476 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3110. Min Range: -4.3110
Max Act: 3.9985. Min Act: -0.1700
Data Index: 3719456 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3110. Min Range: -4.3110
Max Act: 4.0297. Min Act: -0.1700
Data Index: 4663123 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3110. Min Range: -4.3110
Max Act: 3.9360. Min Act: -0.1700
Data Index: 6978473 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3110. Min Range: -4.3110
Max Act: 3.8734. Min Act: -0.1700
Data Index: 221306 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3110. Min Range: -4.3110
Max Act: 3.8734. Min Act: -0.1700
Data Index: 221307 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3110. Min Range: -4.3110
Max Act: 3.9047. Min Act: -0.1700
Data Index: 7661852 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3110. Min Range: -4.3110
Max Act: 3.8734. Min Act: -0.1700
Data Index: 5099525 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3110. Min Range: -4.3110
Max Act: 3.8734. Min Act: -0.1700
Data Index: 7829766 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3110. Min Range: -4.3110
Max Act: 3.8421. Min Act: -0.1700
Data Index: 4663122 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3110. Min Range: -4.3110
Max Act: 3.8109. Min Act: -0.1700
Data Index: 6978474 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3110. Min Range: -4.3110
Max Act: 3.7796. Min Act: -0.1700
Data Index: 1681906 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3110. Min Range: -4.3110
Max Act: 3.7483. Min Act: -0.1700
Data Index: 2518972 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3110. Min Range: -4.3110
Max Act: 3.7796. Min Act: -0.1700
Data Index: 5664436 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3110. Min Range: -4.3110
Max Act: 3.7796. Min Act: -0.1700
Data Index: 1027507 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3110. Min Range: -4.3110
Max Act: 3.7483. Min Act: -0.1700
Data Index: 4663124 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3110. Min Range: -4.3110
Max Act: 3.7483. Min Act: -0.1700
Data Index: 4538541 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19