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

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

Neuron 40 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1566. Min Range: -3.1566

Max Act: 2.6958. Min Act: -0.0000

Data Index: 819395 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 3.1566. Min Range: -3.1566

Max Act: 2.9703. Min Act: -0.0000

Data Index: 529871 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 3.1566. Min Range: -3.1566

Max Act: 2.7315. Min Act: -0.0000

Data Index: 1285170 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 3.1566. Min Range: -3.1566

Max Act: 3.1566. Min Act: -0.0000

Data Index: 161997 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 3.1566. Min Range: -3.1566

Max Act: 2.7434. Min Act: -0.0000

Data Index: 1244023 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 3.1566. Min Range: -3.1566

Max Act: 2.8764. Min Act: -0.0000

Data Index: 1145364 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 3.1566. Min Range: -3.1566

Max Act: 2.7110. Min Act: -0.0000

Data Index: 878237 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 3.1566. Min Range: -3.1566

Max Act: 2.8102. Min Act: -0.0000

Data Index: 46840 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 3.1566. Min Range: -3.1566

Max Act: 2.8169. Min Act: -0.0000

Data Index: 972094 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 3.1566. Min Range: -3.1566

Max Act: 2.6323. Min Act: -0.0000

Data Index: 721874 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 3.1566. Min Range: -3.1566

Max Act: 2.9946. Min Act: -0.0000

Data Index: 125536 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 3.1566. Min Range: -3.1566

Max Act: 2.5385. Min Act: -0.0000

Data Index: 96406 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 3.1566. Min Range: -3.1566

Max Act: 2.3793. Min Act: -0.0000

Data Index: 912981 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 3.1566. Min Range: -3.1566

Max Act: 2.6240. Min Act: -0.0000

Data Index: 276200 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 3.1566. Min Range: -3.1566

Max Act: 2.4889. Min Act: -0.0000

Data Index: 487562 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 3.1566. Min Range: -3.1566

Max Act: 2.5689. Min Act: -0.0000

Data Index: 311499 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 3.1566. Min Range: -3.1566

Max Act: 2.1667. Min Act: -0.0000

Data Index: 836442 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 3.1566. Min Range: -3.1566

Max Act: 2.5072. Min Act: -0.0000

Data Index: 1156616 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 3.1566. Min Range: -3.1566

Max Act: 2.4570. Min Act: -0.0000

Data Index: 1327905 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 3.1566. Min Range: -3.1566

Max Act: 2.4417. Min Act: -0.0000

Data Index: 699392 (C4 (Web Text))

Max Activating Token Index: 494