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

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

Neuron 994 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: 1.1299. Min Range: -1.1299

Max Act: 1.1299. Min Act: -0.0000

Data Index: 1103513 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 1.1299. Min Range: -1.1299

Max Act: 1.0326. Min Act: -0.0000

Data Index: 714880 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 1.1299. Min Range: -1.1299

Max Act: 1.0473. Min Act: -0.0000

Data Index: 624387 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 1.1299. Min Range: -1.1299

Max Act: 1.0030. Min Act: -0.0000

Data Index: 28777 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 1.1299. Min Range: -1.1299

Max Act: 0.8092. Min Act: -0.0000

Data Index: 67266 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 1.1299. Min Range: -1.1299

Max Act: 0.7493. Min Act: -0.0000

Data Index: 1225870 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 1.1299. Min Range: -1.1299

Max Act: 0.6922. Min Act: -0.0000

Data Index: 441944 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 1.1299. Min Range: -1.1299

Max Act: 0.6837. Min Act: -0.0000

Data Index: 137886 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 1.1299. Min Range: -1.1299

Max Act: 0.7067. Min Act: -0.0000

Data Index: 1089058 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 1.1299. Min Range: -1.1299

Max Act: 0.6432. Min Act: -0.0000

Data Index: 707791 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 1.1299. Min Range: -1.1299

Max Act: 0.6616. Min Act: -0.0000

Data Index: 740343 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 1.1299. Min Range: -1.1299

Max Act: 0.6178. Min Act: -0.0000

Data Index: 339439 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 1.1299. Min Range: -1.1299

Max Act: 0.6552. Min Act: -0.0000

Data Index: 155023 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 1.1299. Min Range: -1.1299

Max Act: 0.6402. Min Act: -0.0000

Data Index: 398208 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 1.1299. Min Range: -1.1299

Max Act: 0.6588. Min Act: -0.0000

Data Index: 598041 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 1.1299. Min Range: -1.1299

Max Act: 0.6502. Min Act: -0.0000

Data Index: 900852 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 1.1299. Min Range: -1.1299

Max Act: 0.6230. Min Act: -0.0000

Data Index: 797508 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 1.1299. Min Range: -1.1299

Max Act: 0.5920. Min Act: -0.0000

Data Index: 882770 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 1.1299. Min Range: -1.1299

Max Act: 0.5775. Min Act: -0.0000

Data Index: 530229 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 1.1299. Min Range: -1.1299

Max Act: 0.5713. Min Act: -0.0000

Data Index: 622214 (C4 (Web Text))

Max Activating Token Index: 509