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

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

Neuron 748 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.4546. Min Act: -0.0001

Data Index: 245463 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.4388. Min Act: -0.0001

Data Index: 695472 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3756. Min Act: -0.0001

Data Index: 345622 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3433. Min Act: -0.0001

Data Index: 201945 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3692. Min Act: -0.0001

Data Index: 150043 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3823. Min Act: -0.0001

Data Index: 646129 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3313. Min Act: -0.0001

Data Index: 348097 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3151. Min Act: -0.0001

Data Index: 808532 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.3570. Min Act: -0.0001

Data Index: 772610 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.2877. Min Act: -0.0001

Data Index: 193419 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.2784. Min Act: -0.0001

Data Index: 271313 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.2623. Min Act: -0.0001

Data Index: 1212114 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.2881. Min Act: -0.0001

Data Index: 332344 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.2454. Min Act: -0.0001

Data Index: 23607 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.2839. Min Act: -0.0001

Data Index: 112959 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.2514. Min Act: -0.0001

Data Index: 760122 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.2791. Min Act: -0.0001

Data Index: 1359152 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.2469. Min Act: -0.0001

Data Index: 226047 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.2368. Min Act: -0.0001

Data Index: 251079 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 0.4546. Min Range: -0.4546

Max Act: 0.2401. Min Act: -0.0001

Data Index: 98668 (C4 (Web Text))

Max Activating Token Index: 561