Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 603 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4629. Min Range: -4.4629
Max Act: 4.4629. Min Act: -0.1700
Data Index: 5198687 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4629. Min Range: -4.4629
Max Act: 4.4316. Min Act: -0.1700
Data Index: 5969191 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4629. Min Range: -4.4629
Max Act: 4.3691. Min Act: -0.1700
Data Index: 1346505 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4629. Min Range: -4.4629
Max Act: 4.3691. Min Act: -0.1700
Data Index: 4816731 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4629. Min Range: -4.4629
Max Act: 4.3378. Min Act: -0.1700
Data Index: 694008 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4629. Min Range: -4.4629
Max Act: 4.3378. Min Act: -0.1700
Data Index: 4083929 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4629. Min Range: -4.4629
Max Act: 4.3066. Min Act: -0.1700
Data Index: 1945146 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4629. Min Range: -4.4629
Max Act: 4.3066. Min Act: -0.1700
Data Index: 4244160 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4629. Min Range: -4.4629
Max Act: 4.3378. Min Act: -0.1700
Data Index: 1587395 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4629. Min Range: -4.4629
Max Act: 4.2441. Min Act: -0.1700
Data Index: 4553838 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4629. Min Range: -4.4629
Max Act: 4.2753. Min Act: -0.1700
Data Index: 1019029 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4629. Min Range: -4.4629
Max Act: 4.2753. Min Act: -0.1700
Data Index: 1535527 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4629. Min Range: -4.4629
Max Act: 4.2753. Min Act: -0.1700
Data Index: 2626045 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4629. Min Range: -4.4629
Max Act: 4.3066. Min Act: -0.1700
Data Index: 8211173 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4629. Min Range: -4.4629
Max Act: 4.2753. Min Act: -0.1700
Data Index: 27092 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4629. Min Range: -4.4629
Max Act: 4.2441. Min Act: -0.1700
Data Index: 3674992 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4629. Min Range: -4.4629
Max Act: 4.2128. Min Act: -0.1700
Data Index: 4730299 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4629. Min Range: -4.4629
Max Act: 4.2441. Min Act: -0.1700
Data Index: 916072 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4629. Min Range: -4.4629
Max Act: 4.2441. Min Act: -0.1700
Data Index: 5553249 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4629. Min Range: -4.4629
Max Act: 4.2753. Min Act: -0.1700
Data Index: 3500709 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19