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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 698 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.8157. Min Act: -0.0000

Data Index: 426494 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.6755. Min Act: -0.0000

Data Index: 1272365 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.5265. Min Act: -0.0001

Data Index: 293542 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.3784. Min Act: -0.0000

Data Index: 1200754 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.3948. Min Act: -0.0000

Data Index: 1085634 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.4943. Min Act: -0.0000

Data Index: 1331407 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.3613. Min Act: -0.0000

Data Index: 735527 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.0980. Min Act: -0.0000

Data Index: 603899 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.0598. Min Act: -0.0000

Data Index: 1112829 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.1180. Min Act: -0.0000

Data Index: 1321153 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.2108. Min Act: -0.0000

Data Index: 939534 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.2150. Min Act: -0.0000

Data Index: 423674 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.1990. Min Act: -0.0000

Data Index: 422347 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.1402. Min Act: -0.0000

Data Index: 345216 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.0235. Min Act: -0.0000

Data Index: 106151 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 2.8157. Min Range: -2.8157

Max Act: 1.9724. Min Act: -0.0000

Data Index: 104279 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.0871. Min Act: -0.0000

Data Index: 875236 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.0715. Min Act: -0.0000

Data Index: 564320 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 2.8157. Min Range: -2.8157

Max Act: 2.0707. Min Act: -0.0000

Data Index: 192816 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 2.8157. Min Range: -2.8157

Max Act: 1.8558. Min Act: -0.0000

Data Index: 930775 (C4 (Web Text))

Max Activating Token Index: 775