Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2421 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4809. Min Range: -6.4809
Max Act: 6.4184. Min Act: -0.1700
Data Index: 4637247 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4809. Min Range: -6.4809
Max Act: 6.4809. Min Act: -0.1700
Data Index: 6967932 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4809. Min Range: -6.4809
Max Act: 6.4184. Min Act: -0.1700
Data Index: 1911035 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4809. Min Range: -6.4809
Max Act: 6.3872. Min Act: -0.1700
Data Index: 7852988 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4809. Min Range: -6.4809
Max Act: 6.3559. Min Act: -0.1700
Data Index: 1190290 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4809. Min Range: -6.4809
Max Act: 6.3247. Min Act: -0.1700
Data Index: 2532402 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4809. Min Range: -6.4809
Max Act: 6.3247. Min Act: -0.1700
Data Index: 7163609 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4809. Min Range: -6.4809
Max Act: 6.2934. Min Act: -0.1700
Data Index: 6667628 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4809. Min Range: -6.4809
Max Act: 6.2622. Min Act: -0.1700
Data Index: 1565007 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4809. Min Range: -6.4809
Max Act: 6.2622. Min Act: -0.1700
Data Index: 8792920 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4809. Min Range: -6.4809
Max Act: 6.1684. Min Act: -0.1700
Data Index: 6474693 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4809. Min Range: -6.4809
Max Act: 6.1684. Min Act: -0.1700
Data Index: 7481039 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4809. Min Range: -6.4809
Max Act: 6.1684. Min Act: -0.1700
Data Index: 8166464 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4809. Min Range: -6.4809
Max Act: 6.1684. Min Act: -0.1700
Data Index: 5548707 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4809. Min Range: -6.4809
Max Act: 6.1372. Min Act: -0.1700
Data Index: 4441081 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4809. Min Range: -6.4809
Max Act: 6.1372. Min Act: -0.1700
Data Index: 3383998 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4809. Min Range: -6.4809
Max Act: 6.1059. Min Act: -0.1700
Data Index: 2469732 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4809. Min Range: -6.4809
Max Act: 6.1059. Min Act: -0.1700
Data Index: 6898425 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4809. Min Range: -6.4809
Max Act: 6.1059. Min Act: -0.1700
Data Index: 1772786 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4809. Min Range: -6.4809
Max Act: 6.0747. Min Act: -0.1700
Data Index: 647351 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19