Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3200 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.2056. Min Act: -0.0000

Data Index: 683671 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1974. Min Act: -0.0000

Data Index: 470391 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1785. Min Act: -0.0001

Data Index: 40518 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1604. Min Act: -0.0001

Data Index: 1273203 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1701. Min Act: -0.0001

Data Index: 469124 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1569. Min Act: -0.0001

Data Index: 801578 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1723. Min Act: -0.0001

Data Index: 1114207 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1684. Min Act: -0.0000

Data Index: 147073 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1670. Min Act: -0.0001

Data Index: 1340128 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1542. Min Act: -0.0001

Data Index: 178522 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1595. Min Act: -0.0000

Data Index: 320363 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1545. Min Act: -0.0001

Data Index: 159715 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1533. Min Act: -0.0001

Data Index: 957921 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1379. Min Act: -0.0001

Data Index: 491286 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1468. Min Act: -0.0001

Data Index: 329639 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1503. Min Act: -0.0001

Data Index: 628479 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1441. Min Act: -0.0001

Data Index: 626194 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1561. Min Act: -0.0001

Data Index: 296989 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1399. Min Act: -0.0001

Data Index: 735446 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1389. Min Act: -0.0001

Data Index: 1332561 (C4 (Web Text))

Max Activating Token Index: 991