Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3826 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0421. Min Range: -4.0421
Max Act: 4.0421. Min Act: -0.1700
Data Index: 455733 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.9171. Min Act: -0.1700
Data Index: 5786745 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.8546. Min Act: -0.1700
Data Index: 2247700 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.8546. Min Act: -0.1700
Data Index: 8704006 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.8546. Min Act: -0.1700
Data Index: 2824455 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.8233. Min Act: -0.1700
Data Index: 3439235 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.8233. Min Act: -0.1700
Data Index: 289952 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.8233. Min Act: -0.1700
Data Index: 3632303 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.8233. Min Act: -0.1700
Data Index: 8082107 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.7920. Min Act: -0.1700
Data Index: 3211718 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.7920. Min Act: -0.1700
Data Index: 8147275 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.7920. Min Act: -0.1700
Data Index: 3167161 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.7920. Min Act: -0.1700
Data Index: 5581858 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.8233. Min Act: -0.1700
Data Index: 7356173 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.7920. Min Act: -0.1700
Data Index: 4239963 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.7920. Min Act: -0.1700
Data Index: 7066365 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.7920. Min Act: -0.1700
Data Index: 6938956 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.7920. Min Act: -0.1700
Data Index: 904113 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.7920. Min Act: -0.1700
Data Index: 6212579 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0421. Min Range: -4.0421
Max Act: 3.7920. Min Act: -0.1700
Data Index: 2727561 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19