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

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

Neuron 239 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1841. Min Range: -2.1841

Max Act: 2.1841. Min Act: -0.0000

Data Index: 30164 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 2.1841. Min Range: -2.1841

Max Act: 2.0333. Min Act: -0.0000

Data Index: 620499 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 2.1841. Min Range: -2.1841

Max Act: 1.8648. Min Act: -0.0000

Data Index: 292104 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 2.1841. Min Range: -2.1841

Max Act: 1.9257. Min Act: -0.0000

Data Index: 1595939 (Python Code)

Max Activating Token Index: 673

Text #4

Max Range: 2.1841. Min Range: -2.1841

Max Act: 1.8465. Min Act: -0.0000

Data Index: 278486 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 2.1841. Min Range: -2.1841

Max Act: 1.8201. Min Act: -0.0000

Data Index: 870509 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 2.1841. Min Range: -2.1841

Max Act: 1.9195. Min Act: -0.0000

Data Index: 1151051 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 2.1841. Min Range: -2.1841

Max Act: 1.8154. Min Act: -0.0000

Data Index: 73342 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 2.1841. Min Range: -2.1841

Max Act: 1.7920. Min Act: -0.0000

Data Index: 1344399 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 2.1841. Min Range: -2.1841

Max Act: 1.7322. Min Act: -0.0000

Data Index: 825157 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 2.1841. Min Range: -2.1841

Max Act: 1.6775. Min Act: -0.0000

Data Index: 866853 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 2.1841. Min Range: -2.1841

Max Act: 1.7472. Min Act: -0.0000

Data Index: 1290629 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 2.1841. Min Range: -2.1841

Max Act: 1.9069. Min Act: -0.0000

Data Index: 1520354 (Python Code)

Max Activating Token Index: 753

Text #13

Max Range: 2.1841. Min Range: -2.1841

Max Act: 1.7486. Min Act: -0.0000

Data Index: 809805 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 2.1841. Min Range: -2.1841

Max Act: 1.6965. Min Act: -0.0000

Data Index: 1053063 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 2.1841. Min Range: -2.1841

Max Act: 1.6959. Min Act: -0.0000

Data Index: 605647 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 2.1841. Min Range: -2.1841

Max Act: 1.6952. Min Act: -0.0000

Data Index: 1162181 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 2.1841. Min Range: -2.1841

Max Act: 1.6750. Min Act: -0.0000

Data Index: 300431 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 2.1841. Min Range: -2.1841

Max Act: 1.6640. Min Act: -0.0000

Data Index: 40879 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 2.1841. Min Range: -2.1841

Max Act: 1.6018. Min Act: -0.0000

Data Index: 556047 (C4 (Web Text))

Max Activating Token Index: 687