Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2966 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5827. Min Range: -2.5827
Max Act: 2.5827. Min Act: -0.1700
Data Index: 5653984 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5827. Min Range: -2.5827
Max Act: 2.3554. Min Act: -0.1700
Data Index: 4540681 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5827. Min Range: -2.5827
Max Act: 2.3062. Min Act: -0.1700
Data Index: 3837622 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5827. Min Range: -2.5827
Max Act: 2.2897. Min Act: -0.1700
Data Index: 4396680 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5827. Min Range: -2.5827
Max Act: 2.2897. Min Act: -0.1700
Data Index: 287549 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5827. Min Range: -2.5827
Max Act: 2.2402. Min Act: -0.1700
Data Index: 7901921 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5827. Min Range: -2.5827
Max Act: 2.2567. Min Act: -0.1700
Data Index: 3973316 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5827. Min Range: -2.5827
Max Act: 2.2402. Min Act: -0.1700
Data Index: 826871 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5827. Min Range: -2.5827
Max Act: 2.2071. Min Act: -0.1700
Data Index: 6995162 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5827. Min Range: -2.5827
Max Act: 2.2237. Min Act: -0.1700
Data Index: 2167998 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5827. Min Range: -2.5827
Max Act: 2.2237. Min Act: -0.1700
Data Index: 884326 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5827. Min Range: -2.5827
Max Act: 2.2071. Min Act: -0.1700
Data Index: 2021461 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5827. Min Range: -2.5827
Max Act: 2.2237. Min Act: -0.1700
Data Index: 8124897 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5827. Min Range: -2.5827
Max Act: 2.2071. Min Act: -0.1700
Data Index: 3580521 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5827. Min Range: -2.5827
Max Act: 2.2237. Min Act: -0.1700
Data Index: 1508847 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5827. Min Range: -2.5827
Max Act: 2.2071. Min Act: -0.1700
Data Index: 5949148 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5827. Min Range: -2.5827
Max Act: 2.1905. Min Act: -0.1700
Data Index: 6600571 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5827. Min Range: -2.5827
Max Act: 2.1905. Min Act: -0.1700
Data Index: 1881270 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5827. Min Range: -2.5827
Max Act: 2.1905. Min Act: -0.1700
Data Index: 662886 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5827. Min Range: -2.5827
Max Act: 2.1905. Min Act: -0.1700
Data Index: 6985833 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19