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

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

Neuron 2850 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.3080. Min Act: -0.0000

Data Index: 185369 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2427. Min Act: -0.0000

Data Index: 983944 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2319. Min Act: -0.0000

Data Index: 261815 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2419. Min Act: -0.0000

Data Index: 412944 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2240. Min Act: -0.0000

Data Index: 719343 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2193. Min Act: -0.0000

Data Index: 896409 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2064. Min Act: -0.0000

Data Index: 440456 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2141. Min Act: -0.0000

Data Index: 485237 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2053. Min Act: -0.0000

Data Index: 912409 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2231. Min Act: -0.0000

Data Index: 406406 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2180. Min Act: -0.0000

Data Index: 18330 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.1910. Min Act: -0.0000

Data Index: 889998 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.1949. Min Act: -0.0000

Data Index: 268775 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2012. Min Act: -0.0000

Data Index: 60312 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.1928. Min Act: -0.0000

Data Index: 673995 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.1945. Min Act: -0.0000

Data Index: 674600 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1157405 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.1852. Min Act: -0.0000

Data Index: 502520 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.1914. Min Act: -0.0000

Data Index: 1212065 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.1934. Min Act: -0.0000

Data Index: 839700 (C4 (Web Text))

Max Activating Token Index: 983