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

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

Neuron 4833 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1407. Min Range: -2.1407

Max Act: 2.1407. Min Act: -0.0000

Data Index: 631789 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.6036. Min Act: -0.0000

Data Index: 355825 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.6681. Min Act: -0.0000

Data Index: 312621 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.6748. Min Act: -0.0000

Data Index: 886802 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.5739. Min Act: -0.0000

Data Index: 996247 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.5435. Min Act: -0.0000

Data Index: 467204 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.4573. Min Act: -0.0000

Data Index: 31347 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.4857. Min Act: -0.0000

Data Index: 97248 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.3477. Min Act: -0.0000

Data Index: 1004216 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.2868. Min Act: -0.0000

Data Index: 80015 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.2401. Min Act: -0.0000

Data Index: 880524 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.2532. Min Act: -0.0000

Data Index: 700022 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.3604. Min Act: -0.0000

Data Index: 1245579 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.3433. Min Act: -0.0000

Data Index: 262336 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.2413. Min Act: -0.0000

Data Index: 328167 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.2708. Min Act: -0.0000

Data Index: 206270 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.2693. Min Act: -0.0000

Data Index: 1000271 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.2612. Min Act: -0.0000

Data Index: 951002 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.1669. Min Act: -0.0000

Data Index: 72218 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 2.1407. Min Range: -2.1407

Max Act: 1.1954. Min Act: -0.0000

Data Index: 69953 (C4 (Web Text))

Max Activating Token Index: 287