Model: None
Dataset: The Pile
Neuron 3006 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 5.2457. Min Range: -5.2457
Max Act: 5.2457. Min Act: -0.1700
Data Index: 9326349 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2457. Min Range: -5.2457
Max Act: 5.2144. Min Act: -0.1700
Data Index: 2545361 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2457. Min Range: -5.2457
Max Act: 5.1207. Min Act: -0.1700
Data Index: 3081131 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2457. Min Range: -5.2457
Max Act: 4.9644. Min Act: -0.1700
Data Index: 6920439 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2457. Min Range: -5.2457
Max Act: 4.9332. Min Act: -0.1700
Data Index: 3995346 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2457. Min Range: -5.2457
Max Act: 4.9019. Min Act: -0.1700
Data Index: 4180450 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2457. Min Range: -5.2457
Max Act: 4.8707. Min Act: -0.1700
Data Index: 963444 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2457. Min Range: -5.2457
Max Act: 4.8707. Min Act: -0.1700
Data Index: 10412756 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2457. Min Range: -5.2457
Max Act: 4.8707. Min Act: -0.1700
Data Index: 7946680 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2457. Min Range: -5.2457
Max Act: 4.8707. Min Act: -0.1700
Data Index: 8057349 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2457. Min Range: -5.2457
Max Act: 4.8394. Min Act: -0.1700
Data Index: 2860455 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2457. Min Range: -5.2457
Max Act: 4.8394. Min Act: -0.1700
Data Index: 5969395 (The Pile)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2457. Min Range: -5.2457
Max Act: 4.8082. Min Act: -0.1700
Data Index: 8400819 (The Pile)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2457. Min Range: -5.2457
Max Act: 4.7769. Min Act: -0.1700
Data Index: 3908973 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2457. Min Range: -5.2457
Max Act: 4.7769. Min Act: -0.1700
Data Index: 4926244 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2457. Min Range: -5.2457
Max Act: 4.7769. Min Act: -0.1700
Data Index: 2091555 (The Pile)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2457. Min Range: -5.2457
Max Act: 4.7769. Min Act: -0.1700
Data Index: 9037581 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2457. Min Range: -5.2457
Max Act: 4.7457. Min Act: -0.1700
Data Index: 5580804 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2457. Min Range: -5.2457
Max Act: 4.7457. Min Act: -0.1700
Data Index: 6521539 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2457. Min Range: -5.2457
Max Act: 4.7457. Min Act: -0.1700
Data Index: 4495743 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19