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

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

Neuron 1659 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4307. Min Range: -4.4307

Max Act: 4.4307. Min Act: -0.0000

Data Index: 1288992 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 4.4307. Min Range: -4.4307

Max Act: 4.3481. Min Act: -0.0000

Data Index: 1094284 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 4.4307. Min Range: -4.4307

Max Act: 4.1814. Min Act: -0.0000

Data Index: 510870 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 4.4307. Min Range: -4.4307

Max Act: 4.1428. Min Act: -0.0000

Data Index: 73034 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 4.4307. Min Range: -4.4307

Max Act: 3.9598. Min Act: -0.0000

Data Index: 227213 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 4.4307. Min Range: -4.4307

Max Act: 3.5337. Min Act: -0.0000

Data Index: 236439 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 4.4307. Min Range: -4.4307

Max Act: 3.5012. Min Act: -0.0000

Data Index: 160649 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 4.4307. Min Range: -4.4307

Max Act: 3.3825. Min Act: -0.0000

Data Index: 914470 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 4.4307. Min Range: -4.4307

Max Act: 3.2249. Min Act: -0.0000

Data Index: 943343 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 4.4307. Min Range: -4.4307

Max Act: 3.2333. Min Act: -0.0000

Data Index: 1126688 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 4.4307. Min Range: -4.4307

Max Act: 3.2165. Min Act: -0.0000

Data Index: 76725 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 4.4307. Min Range: -4.4307

Max Act: 3.2302. Min Act: -0.0000

Data Index: 1210446 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 4.4307. Min Range: -4.4307

Max Act: 3.2176. Min Act: -0.0000

Data Index: 747802 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 4.4307. Min Range: -4.4307

Max Act: 3.0906. Min Act: -0.0000

Data Index: 331603 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 4.4307. Min Range: -4.4307

Max Act: 3.0577. Min Act: -0.0000

Data Index: 1145339 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 4.4307. Min Range: -4.4307

Max Act: 3.0413. Min Act: -0.0000

Data Index: 657848 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 4.4307. Min Range: -4.4307

Max Act: 3.1793. Min Act: -0.0000

Data Index: 1030429 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 4.4307. Min Range: -4.4307

Max Act: 3.1489. Min Act: -0.0001

Data Index: 523330 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 4.4307. Min Range: -4.4307

Max Act: 3.1506. Min Act: -0.0000

Data Index: 1298837 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 4.4307. Min Range: -4.4307

Max Act: 2.8511. Min Act: -0.0000

Data Index: 1341874 (C4 (Web Text))

Max Activating Token Index: 701