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

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

Neuron 1067 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: 2.2451. Min Range: -2.2451

Max Act: 2.2363. Min Act: -0.0000

Data Index: 96405 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 2.2451. Min Range: -2.2451

Max Act: 2.2451. Min Act: -0.0000

Data Index: 802686 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 2.2451. Min Range: -2.2451

Max Act: 2.1883. Min Act: -0.0000

Data Index: 387834 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 2.2451. Min Range: -2.2451

Max Act: 2.0981. Min Act: -0.0000

Data Index: 1250724 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 2.2451. Min Range: -2.2451

Max Act: 2.0010. Min Act: -0.0000

Data Index: 640618 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 2.2451. Min Range: -2.2451

Max Act: 2.1863. Min Act: -0.0000

Data Index: 281180 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 2.2451. Min Range: -2.2451

Max Act: 1.9203. Min Act: -0.0000

Data Index: 1338941 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 2.2451. Min Range: -2.2451

Max Act: 1.9706. Min Act: -0.0000

Data Index: 851751 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 2.2451. Min Range: -2.2451

Max Act: 1.9297. Min Act: -0.0000

Data Index: 128156 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 2.2451. Min Range: -2.2451

Max Act: 1.8610. Min Act: -0.0000

Data Index: 310157 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 2.2451. Min Range: -2.2451

Max Act: 2.0180. Min Act: -0.0000

Data Index: 1047634 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 2.2451. Min Range: -2.2451

Max Act: 1.9352. Min Act: -0.0000

Data Index: 213981 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 2.2451. Min Range: -2.2451

Max Act: 1.8254. Min Act: -0.0001

Data Index: 1407894 (Python Code)

Max Activating Token Index: 133

Text #13

Max Range: 2.2451. Min Range: -2.2451

Max Act: 1.9568. Min Act: -0.0000

Data Index: 868823 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 2.2451. Min Range: -2.2451

Max Act: 1.8880. Min Act: -0.0001

Data Index: 1502962 (Python Code)

Max Activating Token Index: 354

Text #15

Max Range: 2.2451. Min Range: -2.2451

Max Act: 1.8726. Min Act: -0.0000

Data Index: 400333 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 2.2451. Min Range: -2.2451

Max Act: 1.9338. Min Act: -0.0000

Data Index: 446216 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 2.2451. Min Range: -2.2451

Max Act: 1.8594. Min Act: -0.0001

Data Index: 1525516 (Python Code)

Max Activating Token Index: 582

Text #18

Max Range: 2.2451. Min Range: -2.2451

Max Act: 1.8133. Min Act: -0.0000

Data Index: 600671 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 2.2451. Min Range: -2.2451

Max Act: 1.8288. Min Act: -0.0000

Data Index: 856542 (C4 (Web Text))

Max Activating Token Index: 923