Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 905 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1226. Min Range: -2.1226
Max Act: 2.1226. Min Act: -0.1700
Data Index: 2525807 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1226. Min Range: -2.1226
Max Act: 2.1226. Min Act: -0.1700
Data Index: 7681191 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1226. Min Range: -2.1226
Max Act: 2.1059. Min Act: -0.1700
Data Index: 3930943 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1226. Min Range: -2.1226
Max Act: 2.0724. Min Act: -0.1700
Data Index: 8220411 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1226. Min Range: -2.1226
Max Act: 2.0556. Min Act: -0.1700
Data Index: 2201525 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1226. Min Range: -2.1226
Max Act: 2.0388. Min Act: -0.1700
Data Index: 1680642 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1226. Min Range: -2.1226
Max Act: 2.0388. Min Act: -0.1700
Data Index: 4312887 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1226. Min Range: -2.1226
Max Act: 2.0388. Min Act: -0.1700
Data Index: 1017128 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1226. Min Range: -2.1226
Max Act: 2.0388. Min Act: -0.1700
Data Index: 1502466 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1226. Min Range: -2.1226
Max Act: 2.0050. Min Act: -0.1700
Data Index: 6042421 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1226. Min Range: -2.1226
Max Act: 2.0050. Min Act: -0.1700
Data Index: 7027613 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1226. Min Range: -2.1226
Max Act: 2.0219. Min Act: -0.1700
Data Index: 6929621 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1226. Min Range: -2.1226
Max Act: 1.9966. Min Act: -0.1700
Data Index: 7453370 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1226. Min Range: -2.1226
Max Act: 1.9966. Min Act: -0.1700
Data Index: 6066448 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1226. Min Range: -2.1226
Max Act: 1.9881. Min Act: -0.1700
Data Index: 1006544 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1226. Min Range: -2.1226
Max Act: 1.9881. Min Act: -0.1700
Data Index: 3377755 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1226. Min Range: -2.1226
Max Act: 1.9966. Min Act: -0.1700
Data Index: 7852240 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1226. Min Range: -2.1226
Max Act: 1.9881. Min Act: -0.1700
Data Index: 8380726 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1226. Min Range: -2.1226
Max Act: 1.9712. Min Act: -0.1700
Data Index: 4434950 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1226. Min Range: -2.1226
Max Act: 1.9797. Min Act: -0.1700
Data Index: 2210717 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19