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

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

Neuron 5170 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: 1.5423. Min Range: -1.5423

Max Act: 1.5423. Min Act: -0.0000

Data Index: 1149639 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.2753. Min Act: -0.0000

Data Index: 22812 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.0208. Min Act: -0.0000

Data Index: 17263 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.0645. Min Act: -0.0000

Data Index: 657454 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.0534. Min Act: -0.0000

Data Index: 932073 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.0364. Min Act: -0.0000

Data Index: 898950 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 1.5423. Min Range: -1.5423

Max Act: 0.9392. Min Act: -0.0000

Data Index: 547254 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.0050. Min Act: -0.0000

Data Index: 65347 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 1.5423. Min Range: -1.5423

Max Act: 0.9662. Min Act: -0.0000

Data Index: 188508 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 1.5423. Min Range: -1.5423

Max Act: 0.9801. Min Act: -0.0000

Data Index: 1010471 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 1.5423. Min Range: -1.5423

Max Act: 1.1107. Min Act: -0.0000

Data Index: 660661 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 1.5423. Min Range: -1.5423

Max Act: 0.8693. Min Act: -0.0000

Data Index: 952667 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 1.5423. Min Range: -1.5423

Max Act: 0.9876. Min Act: -0.0000

Data Index: 1035852 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 1.5423. Min Range: -1.5423

Max Act: 0.9161. Min Act: -0.0000

Data Index: 111034 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 1.5423. Min Range: -1.5423

Max Act: 0.8542. Min Act: -0.0000

Data Index: 510314 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 1.5423. Min Range: -1.5423

Max Act: 0.9108. Min Act: -0.0000

Data Index: 1295114 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 1.5423. Min Range: -1.5423

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1268405 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 1.5423. Min Range: -1.5423

Max Act: 0.9550. Min Act: -0.0000

Data Index: 1019246 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 1.5423. Min Range: -1.5423

Max Act: 0.9611. Min Act: -0.0000

Data Index: 457153 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 1.5423. Min Range: -1.5423

Max Act: 0.9333. Min Act: -0.0000

Data Index: 52625 (C4 (Web Text))

Max Activating Token Index: 597