Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3128 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.8224. Min Range: -0.8224
Max Act: 0.8224. Min Act: -0.0001
Data Index: 1175395 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8224. Min Range: -0.8224
Max Act: 0.7671. Min Act: -0.0001
Data Index: 1854686 (The Pile)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8224. Min Range: -0.8224
Max Act: 0.7572. Min Act: -0.0001
Data Index: 1634333 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8224. Min Range: -0.8224
Max Act: 0.7291. Min Act: -0.0001
Data Index: 1698609 (The Pile)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8224. Min Range: -0.8224
Max Act: 0.7702. Min Act: -0.0001
Data Index: 1433546 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8224. Min Range: -0.8224
Max Act: 0.7386. Min Act: -0.0001
Data Index: 435396 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8224. Min Range: -0.8224
Max Act: 0.7214. Min Act: -0.0001
Data Index: 295355 (The Pile)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8224. Min Range: -0.8224
Max Act: 0.7202. Min Act: -0.0001
Data Index: 1108105 (The Pile)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8224. Min Range: -0.8224
Max Act: 0.7742. Min Act: -0.0001
Data Index: 850619 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8224. Min Range: -0.8224
Max Act: 0.6873. Min Act: -0.0001
Data Index: 807137 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8224. Min Range: -0.8224
Max Act: 0.8066. Min Act: -0.0001
Data Index: 1849411 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8224. Min Range: -0.8224
Max Act: 0.7718. Min Act: -0.0001
Data Index: 675307 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8224. Min Range: -0.8224
Max Act: 0.7447. Min Act: -0.0001
Data Index: 1609191 (The Pile)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8224. Min Range: -0.8224
Max Act: 0.6932. Min Act: -0.0001
Data Index: 1462046 (The Pile)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8224. Min Range: -0.8224
Max Act: 0.6761. Min Act: -0.0001
Data Index: 1756161 (The Pile)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8224. Min Range: -0.8224
Max Act: 0.6970. Min Act: -0.0001
Data Index: 1801950 (The Pile)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8224. Min Range: -0.8224
Max Act: 0.6702. Min Act: -0.0001
Data Index: 1421957 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8224. Min Range: -0.8224
Max Act: 0.7056. Min Act: -0.0001
Data Index: 856201 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8224. Min Range: -0.8224
Max Act: 0.6910. Min Act: -0.0001
Data Index: 1263935 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8224. Min Range: -0.8224
Max Act: 0.6707. Min Act: -0.0001
Data Index: 1497969 (The Pile)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19