Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3648 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.5180. Min Act: -0.0000

Data Index: 1975584 (The Pile)

Max Activating Token Index: 278

Text #1

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.5269. Min Act: -0.0000

Data Index: 87157 (The Pile)

Max Activating Token Index: 367

Text #2

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.5231. Min Act: -0.0000

Data Index: 1351996 (The Pile)

Max Activating Token Index: 145

Text #3

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1129699 (The Pile)

Max Activating Token Index: 143

Text #4

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3969. Min Act: -0.0001

Data Index: 121524 (The Pile)

Max Activating Token Index: 778

Text #5

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4543. Min Act: -0.0000

Data Index: 103658 (The Pile)

Max Activating Token Index: 187

Text #6

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4174. Min Act: -0.0000

Data Index: 529434 (The Pile)

Max Activating Token Index: 53

Text #7

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3995. Min Act: -0.0000

Data Index: 418226 (The Pile)

Max Activating Token Index: 639

Text #8

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4025. Min Act: -0.0000

Data Index: 1172954 (The Pile)

Max Activating Token Index: 628

Text #9

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4478. Min Act: -0.0000

Data Index: 114456 (The Pile)

Max Activating Token Index: 756

Text #10

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4090. Min Act: -0.0000

Data Index: 1025118 (The Pile)

Max Activating Token Index: 587

Text #11

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4394. Min Act: -0.0000

Data Index: 11492 (The Pile)

Max Activating Token Index: 591

Text #12

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.4309. Min Act: -0.0000

Data Index: 448809 (The Pile)

Max Activating Token Index: 168

Text #13

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3895. Min Act: -0.0000

Data Index: 1822881 (The Pile)

Max Activating Token Index: 974

Text #14

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3406. Min Act: -0.0000

Data Index: 1390037 (The Pile)

Max Activating Token Index: 305

Text #15

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3482. Min Act: -0.0000

Data Index: 1363283 (The Pile)

Max Activating Token Index: 1017

Text #16

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3621. Min Act: -0.0000

Data Index: 1974827 (The Pile)

Max Activating Token Index: 517

Text #17

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3661. Min Act: -0.0000

Data Index: 1670748 (The Pile)

Max Activating Token Index: 255

Text #18

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3521. Min Act: -0.0000

Data Index: 46070 (The Pile)

Max Activating Token Index: 308

Text #19

Max Range: 0.5269. Min Range: -0.5269

Max Act: 0.3867. Min Act: -0.0000

Data Index: 957268 (The Pile)

Max Activating Token Index: 419