Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 37 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0370. Min Range: -6.0370
Max Act: 6.0057. Min Act: -0.1700
Data Index: 1460117 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0370. Min Range: -6.0370
Max Act: 6.0370. Min Act: -0.1700
Data Index: 3982184 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0370. Min Range: -6.0370
Max Act: 5.9432. Min Act: -0.1700
Data Index: 8753421 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0370. Min Range: -6.0370
Max Act: 5.7557. Min Act: -0.1700
Data Index: 6526778 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0370. Min Range: -6.0370
Max Act: 5.7245. Min Act: -0.1700
Data Index: 3014115 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0370. Min Range: -6.0370
Max Act: 5.7557. Min Act: -0.1700
Data Index: 1841173 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0370. Min Range: -6.0370
Max Act: 5.7557. Min Act: -0.1700
Data Index: 4677677 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0370. Min Range: -6.0370
Max Act: 5.6932. Min Act: -0.1700
Data Index: 7514838 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0370. Min Range: -6.0370
Max Act: 5.6932. Min Act: -0.1700
Data Index: 4172673 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0370. Min Range: -6.0370
Max Act: 5.6307. Min Act: -0.1700
Data Index: 4968527 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0370. Min Range: -6.0370
Max Act: 5.5995. Min Act: -0.1700
Data Index: 3584961 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0370. Min Range: -6.0370
Max Act: 5.5682. Min Act: -0.1700
Data Index: 4916783 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0370. Min Range: -6.0370
Max Act: 5.6307. Min Act: -0.1700
Data Index: 680932 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0370. Min Range: -6.0370
Max Act: 5.5370. Min Act: -0.1700
Data Index: 2253588 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0370. Min Range: -6.0370
Max Act: 5.5057. Min Act: -0.1700
Data Index: 5602958 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0370. Min Range: -6.0370
Max Act: 5.4745. Min Act: -0.1700
Data Index: 5960212 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0370. Min Range: -6.0370
Max Act: 5.4745. Min Act: -0.1700
Data Index: 1651966 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0370. Min Range: -6.0370
Max Act: 5.5057. Min Act: -0.1700
Data Index: 3584962 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0370. Min Range: -6.0370
Max Act: 5.4432. Min Act: -0.1700
Data Index: 5842184 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0370. Min Range: -6.0370
Max Act: 5.4432. Min Act: -0.1700
Data Index: 4467227 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19