Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4560 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.3389. Min Act: -0.0000

Data Index: 233877 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2445. Min Act: -0.0000

Data Index: 13872 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2544. Min Act: -0.0000

Data Index: 355259 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2342. Min Act: -0.0000

Data Index: 66379 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2382. Min Act: -0.0000

Data Index: 1156659 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2215. Min Act: -0.0000

Data Index: 122247 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1195066 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2443. Min Act: -0.0000

Data Index: 72850 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2174. Min Act: -0.0000

Data Index: 744666 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2260. Min Act: -0.0000

Data Index: 1239509 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2286. Min Act: -0.0000

Data Index: 988131 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2038. Min Act: -0.0000

Data Index: 533153 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2091. Min Act: -0.0000

Data Index: 201729 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.1867. Min Act: -0.0000

Data Index: 438515 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1299119 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2040. Min Act: -0.0000

Data Index: 881074 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2189. Min Act: -0.0000

Data Index: 1318133 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2115. Min Act: -0.0000

Data Index: 1285551 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1219851 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 0.3389. Min Range: -0.3389

Max Act: 0.2029. Min Act: -0.0000

Data Index: 470477 (C4 (Web Text))

Max Activating Token Index: 605