Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2914 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2183. Min Range: -6.2183
Max Act: 6.2183. Min Act: -0.1700
Data Index: 541634 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2183. Min Range: -6.2183
Max Act: 5.9683. Min Act: -0.1700
Data Index: 5072677 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2183. Min Range: -6.2183
Max Act: 5.8745. Min Act: -0.1700
Data Index: 683009 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2183. Min Range: -6.2183
Max Act: 5.8433. Min Act: -0.1700
Data Index: 6632531 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2183. Min Range: -6.2183
Max Act: 5.7495. Min Act: -0.1700
Data Index: 203636 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2183. Min Range: -6.2183
Max Act: 5.6870. Min Act: -0.1700
Data Index: 1980854 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2183. Min Range: -6.2183
Max Act: 5.6870. Min Act: -0.1700
Data Index: 2823637 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2183. Min Range: -6.2183
Max Act: 5.6245. Min Act: -0.1700
Data Index: 5442489 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2183. Min Range: -6.2183
Max Act: 5.6558. Min Act: -0.1700
Data Index: 110077 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2183. Min Range: -6.2183
Max Act: 5.6245. Min Act: -0.1700
Data Index: 2368821 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2183. Min Range: -6.2183
Max Act: 5.6558. Min Act: -0.1700
Data Index: 85623 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2183. Min Range: -6.2183
Max Act: 5.6245. Min Act: -0.1700
Data Index: 8113619 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2183. Min Range: -6.2183
Max Act: 5.5933. Min Act: -0.1700
Data Index: 3787034 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2183. Min Range: -6.2183
Max Act: 5.5933. Min Act: -0.1700
Data Index: 6327235 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2183. Min Range: -6.2183
Max Act: 5.5620. Min Act: -0.1700
Data Index: 1893260 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2183. Min Range: -6.2183
Max Act: 5.5308. Min Act: -0.1700
Data Index: 2636895 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2183. Min Range: -6.2183
Max Act: 5.5620. Min Act: -0.1700
Data Index: 1492359 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2183. Min Range: -6.2183
Max Act: 5.5620. Min Act: -0.1700
Data Index: 7715569 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2183. Min Range: -6.2183
Max Act: 5.5620. Min Act: -0.1700
Data Index: 592759 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2183. Min Range: -6.2183
Max Act: 5.5620. Min Act: -0.1700
Data Index: 1950599 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19