Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4785 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.9276. Min Act: -0.1700
Data Index: 8752732 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.8959. Min Act: -0.1700
Data Index: 2375573 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.8323. Min Act: -0.1700
Data Index: 6474209 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.8005. Min Act: -0.1699
Data Index: 7164964 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.7686. Min Act: -0.1700
Data Index: 2184483 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.8005. Min Act: -0.1700
Data Index: 7875953 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.8005. Min Act: -0.1700
Data Index: 2522655 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.8005. Min Act: -0.1700
Data Index: 7157873 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.7527. Min Act: -0.1700
Data Index: 5981004 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.7527. Min Act: -0.1700
Data Index: 3686519 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.7367. Min Act: -0.1700
Data Index: 6676737 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.7367. Min Act: -0.1700
Data Index: 2059681 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.7207. Min Act: -0.1700
Data Index: 4558884 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.7047. Min Act: -0.1700
Data Index: 8552716 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.7047. Min Act: -0.1700
Data Index: 1492097 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.6887. Min Act: -0.1700
Data Index: 5949579 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.6887. Min Act: -0.1700
Data Index: 2618322 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.7047. Min Act: -0.1700
Data Index: 2426330 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.6887. Min Act: -0.1700
Data Index: 4093325 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9276. Min Range: -2.9276
Max Act: 2.7047. Min Act: -0.1700
Data Index: 6609996 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19