Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2680 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2497. Min Act: -0.0000

Data Index: 650299 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2271. Min Act: -0.0000

Data Index: 287791 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2233. Min Act: -0.0001

Data Index: 70582 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2197. Min Act: -0.0000

Data Index: 436340 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2077. Min Act: -0.0000

Data Index: 1316195 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2208. Min Act: -0.0000

Data Index: 581101 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2039. Min Act: -0.0000

Data Index: 816974 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2042. Min Act: -0.0000

Data Index: 432454 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1182571 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1961. Min Act: -0.0000

Data Index: 1265624 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1992. Min Act: -0.0000

Data Index: 891860 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1998. Min Act: -0.0000

Data Index: 221749 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1959. Min Act: -0.0000

Data Index: 772070 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2010. Min Act: -0.0000

Data Index: 977986 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1872. Min Act: -0.0000

Data Index: 864227 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1848. Min Act: -0.0000

Data Index: 704972 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1980. Min Act: -0.0000

Data Index: 18876 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1910. Min Act: 0.0000

Data Index: 194278 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1976. Min Act: -0.0000

Data Index: 405829 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1897. Min Act: -0.0000

Data Index: 133971 (C4 (Web Text))

Max Activating Token Index: 347