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

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

Neuron 4420 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.4247. Min Act: -0.0000

Data Index: 255686 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2962. Min Act: -0.0000

Data Index: 51336 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2555. Min Act: -0.0000

Data Index: 113153 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2577. Min Act: -0.0000

Data Index: 606788 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2096. Min Act: -0.0000

Data Index: 378507 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2364. Min Act: -0.0000

Data Index: 33911 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2243. Min Act: -0.0000

Data Index: 192232 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2421. Min Act: -0.0000

Data Index: 416061 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.1922. Min Act: -0.0000

Data Index: 993634 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2211. Min Act: -0.0000

Data Index: 509460 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2189. Min Act: -0.0000

Data Index: 630758 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2261. Min Act: -0.0000

Data Index: 231748 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2172. Min Act: -0.0000

Data Index: 150529 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2136. Min Act: -0.0000

Data Index: 52542 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2155. Min Act: -0.0000

Data Index: 1167572 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.1998. Min Act: -0.0000

Data Index: 27797 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2060. Min Act: -0.0000

Data Index: 692862 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2098. Min Act: -0.0000

Data Index: 805854 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1319415 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 0.4247. Min Range: -0.4247

Max Act: 0.2111. Min Act: -0.0000

Data Index: 126839 (C4 (Web Text))

Max Activating Token Index: 790