Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1324 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5774. Min Range: -4.5774
Max Act: 4.5774. Min Act: -0.1700
Data Index: 6252804 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5774. Min Range: -4.5774
Max Act: 4.5149. Min Act: -0.1700
Data Index: 2617024 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5774. Min Range: -4.5774
Max Act: 4.4837. Min Act: -0.1700
Data Index: 5008043 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5774. Min Range: -4.5774
Max Act: 4.4524. Min Act: -0.1700
Data Index: 4056116 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5774. Min Range: -4.5774
Max Act: 4.4837. Min Act: -0.1700
Data Index: 3637233 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5774. Min Range: -4.5774
Max Act: 4.4837. Min Act: -0.1700
Data Index: 5719597 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5774. Min Range: -4.5774
Max Act: 4.4524. Min Act: -0.1700
Data Index: 7203660 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5774. Min Range: -4.5774
Max Act: 4.4524. Min Act: -0.1700
Data Index: 2544430 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5774. Min Range: -4.5774
Max Act: 4.4524. Min Act: -0.1700
Data Index: 8666181 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5774. Min Range: -4.5774
Max Act: 4.4837. Min Act: -0.1700
Data Index: 7510433 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5774. Min Range: -4.5774
Max Act: 4.4524. Min Act: -0.1700
Data Index: 709235 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5774. Min Range: -4.5774
Max Act: 4.4212. Min Act: -0.1700
Data Index: 5210213 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5774. Min Range: -4.5774
Max Act: 4.3899. Min Act: -0.1700
Data Index: 6520620 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5774. Min Range: -4.5774
Max Act: 4.3899. Min Act: -0.1700
Data Index: 1299735 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5774. Min Range: -4.5774
Max Act: 4.3899. Min Act: -0.1700
Data Index: 3726002 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5774. Min Range: -4.5774
Max Act: 4.3587. Min Act: -0.1700
Data Index: 3362135 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5774. Min Range: -4.5774
Max Act: 4.3274. Min Act: -0.1700
Data Index: 5714925 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5774. Min Range: -4.5774
Max Act: 4.3274. Min Act: -0.1700
Data Index: 6306050 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5774. Min Range: -4.5774
Max Act: 4.3274. Min Act: -0.1700
Data Index: 6409281 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5774. Min Range: -4.5774
Max Act: 4.3274. Min Act: -0.1700
Data Index: 3966000 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19