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

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

Neuron 1197 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: 0.1531. Min Range: -0.1531

Max Act: 0.1531. Min Act: -0.0000

Data Index: 327482 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1395. Min Act: -0.0000

Data Index: 674565 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1459. Min Act: -0.0000

Data Index: 888486 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1312. Min Act: -0.0000

Data Index: 485364 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1345. Min Act: -0.0000

Data Index: 256825 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1327. Min Act: -0.0000

Data Index: 328897 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1321. Min Act: -0.0000

Data Index: 235458 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1245. Min Act: -0.0000

Data Index: 839189 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1217. Min Act: -0.0000

Data Index: 685643 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1220. Min Act: -0.0000

Data Index: 188763 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1207. Min Act: -0.0000

Data Index: 185098 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1184. Min Act: -0.0000

Data Index: 729557 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1167. Min Act: -0.0000

Data Index: 201981 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1162. Min Act: -0.0000

Data Index: 947717 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1211. Min Act: -0.0000

Data Index: 601460 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1202. Min Act: -0.0000

Data Index: 830913 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1203. Min Act: -0.0000

Data Index: 731895 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1183. Min Act: -0.0000

Data Index: 1125690 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1054. Min Act: -0.0000

Data Index: 1063438 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1183. Min Act: -0.0000

Data Index: 826296 (C4 (Web Text))

Max Activating Token Index: 382