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

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

Neuron 3919 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3605. Min Act: -0.0000

Data Index: 1301113 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3368. Min Act: -0.0000

Data Index: 1297623 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3310. Min Act: -0.0000

Data Index: 362023 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3095. Min Act: -0.0000

Data Index: 656931 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2881. Min Act: -0.0000

Data Index: 1137428 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3319. Min Act: -0.0000

Data Index: 943407 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2963. Min Act: -0.0000

Data Index: 1085173 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2971. Min Act: -0.0000

Data Index: 1119541 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2845. Min Act: -0.0000

Data Index: 416244 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2766. Min Act: -0.0000

Data Index: 48768 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2932. Min Act: -0.0000

Data Index: 330382 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2899. Min Act: -0.0000

Data Index: 664783 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2674. Min Act: -0.0000

Data Index: 1246149 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2864. Min Act: -0.0000

Data Index: 175375 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1183398 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2711. Min Act: -0.0000

Data Index: 1079945 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2523. Min Act: -0.0000

Data Index: 336292 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2792. Min Act: -0.0000

Data Index: 1116354 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2671. Min Act: -0.0000

Data Index: 1050417 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2596. Min Act: -0.0000

Data Index: 550657 (C4 (Web Text))

Max Activating Token Index: 826