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

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

Neuron 3743 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0323. Min Range: -3.0323

Max Act: 3.0323. Min Act: -0.0000

Data Index: 1005632 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 3.0323. Min Range: -3.0323

Max Act: 2.8698. Min Act: -0.0000

Data Index: 951987 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 3.0323. Min Range: -3.0323

Max Act: 2.8087. Min Act: -0.0000

Data Index: 1106457 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 3.0323. Min Range: -3.0323

Max Act: 2.6879. Min Act: -0.0000

Data Index: 86587 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 3.0323. Min Range: -3.0323

Max Act: 2.6304. Min Act: -0.0000

Data Index: 524336 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 3.0323. Min Range: -3.0323

Max Act: 2.6250. Min Act: -0.0000

Data Index: 1176153 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 3.0323. Min Range: -3.0323

Max Act: 2.5877. Min Act: -0.0000

Data Index: 62927 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 3.0323. Min Range: -3.0323

Max Act: 2.5345. Min Act: -0.0000

Data Index: 837693 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 3.0323. Min Range: -3.0323

Max Act: 2.3412. Min Act: -0.0000

Data Index: 1277373 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 3.0323. Min Range: -3.0323

Max Act: 2.3417. Min Act: -0.0000

Data Index: 1253835 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 3.0323. Min Range: -3.0323

Max Act: 2.3371. Min Act: -0.0000

Data Index: 253461 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 3.0323. Min Range: -3.0323

Max Act: 2.2135. Min Act: -0.0000

Data Index: 272 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 3.0323. Min Range: -3.0323

Max Act: 2.1633. Min Act: -0.0000

Data Index: 883321 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 3.0323. Min Range: -3.0323

Max Act: 2.1262. Min Act: -0.0000

Data Index: 446788 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 3.0323. Min Range: -3.0323

Max Act: 2.1325. Min Act: -0.0000

Data Index: 973689 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 3.0323. Min Range: -3.0323

Max Act: 2.1876. Min Act: -0.0000

Data Index: 284913 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 3.0323. Min Range: -3.0323

Max Act: 2.0834. Min Act: -0.0000

Data Index: 543940 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 3.0323. Min Range: -3.0323

Max Act: 2.1767. Min Act: -0.0000

Data Index: 943869 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 3.0323. Min Range: -3.0323

Max Act: 1.9352. Min Act: -0.0000

Data Index: 201486 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 3.0323. Min Range: -3.0323

Max Act: 2.1574. Min Act: -0.0000

Data Index: 1308440 (C4 (Web Text))

Max Activating Token Index: 407