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

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

Neuron 300 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2401. Min Act: -0.0001

Data Index: 177378 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2507. Min Act: -0.0001

Data Index: 1037234 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2276. Min Act: -0.0001

Data Index: 878007 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2242. Min Act: -0.0001

Data Index: 1357299 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2241. Min Act: -0.0001

Data Index: 1085662 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2096. Min Act: -0.0001

Data Index: 128844 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2127. Min Act: -0.0001

Data Index: 976698 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2191. Min Act: -0.0001

Data Index: 1081227 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2052. Min Act: -0.0001

Data Index: 476687 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2118. Min Act: -0.0001

Data Index: 1259115 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2110. Min Act: -0.0001

Data Index: 14705 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1956. Min Act: -0.0001

Data Index: 82572 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2012. Min Act: -0.0001

Data Index: 1104678 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2072. Min Act: -0.0001

Data Index: 1346197 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1993. Min Act: -0.0001

Data Index: 855413 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1987. Min Act: -0.0001

Data Index: 1200125 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1918. Min Act: -0.0001

Data Index: 1350330 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1984. Min Act: -0.0001

Data Index: 143191 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1968. Min Act: -0.0001

Data Index: 512864 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1962. Min Act: -0.0001

Data Index: 1076950 (C4 (Web Text))

Max Activating Token Index: 302