Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2444 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 2.8291. Min Range: -2.8291
Max Act: 2.7872. Min Act: -0.0001
Data Index: 1290215 (The Pile)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8291. Min Range: -2.8291
Max Act: 2.8013. Min Act: -0.0000
Data Index: 1612912 (The Pile)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8291. Min Range: -2.8291
Max Act: 2.8291. Min Act: -0.0001
Data Index: 982749 (The Pile)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8291. Min Range: -2.8291
Max Act: 2.7481. Min Act: -0.0001
Data Index: 898626 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8291. Min Range: -2.8291
Max Act: 2.4395. Min Act: -0.0001
Data Index: 967883 (The Pile)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8291. Min Range: -2.8291
Max Act: 2.4482. Min Act: -0.0001
Data Index: 185119 (The Pile)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8291. Min Range: -2.8291
Max Act: 2.5352. Min Act: -0.0001
Data Index: 1401402 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8291. Min Range: -2.8291
Max Act: 2.4831. Min Act: -0.0001
Data Index: 1535251 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8291. Min Range: -2.8291
Max Act: 2.4007. Min Act: -0.0001
Data Index: 274488 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8291. Min Range: -2.8291
Max Act: 2.4933. Min Act: -0.0001
Data Index: 460880 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8291. Min Range: -2.8291
Max Act: 2.4546. Min Act: -0.0001
Data Index: 1029831 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8291. Min Range: -2.8291
Max Act: 2.3098. Min Act: -0.0001
Data Index: 400050 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8291. Min Range: -2.8291
Max Act: 2.1004. Min Act: -0.0001
Data Index: 751335 (The Pile)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8291. Min Range: -2.8291
Max Act: 2.0761. Min Act: -0.0001
Data Index: 629113 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8291. Min Range: -2.8291
Max Act: 2.2804. Min Act: -0.0001
Data Index: 1745458 (The Pile)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8291. Min Range: -2.8291
Max Act: 2.3064. Min Act: -0.0001
Data Index: 1517344 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8291. Min Range: -2.8291
Max Act: 2.1751. Min Act: -0.0001
Data Index: 1462257 (The Pile)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8291. Min Range: -2.8291
Max Act: 2.0134. Min Act: -0.0001
Data Index: 1637109 (The Pile)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8291. Min Range: -2.8291
Max Act: 2.3013. Min Act: -0.0001
Data Index: 1867716 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8291. Min Range: -2.8291
Max Act: 2.2243. Min Act: -0.0001
Data Index: 908755 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19