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

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

Neuron 1574 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: 0.4218. Min Range: -0.4218

Max Act: 0.4218. Min Act: -0.0000

Data Index: 976943 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1023462 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3311. Min Act: -0.0000

Data Index: 1145097 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3409. Min Act: -0.0000

Data Index: 792903 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3310. Min Act: -0.0000

Data Index: 492286 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.2653. Min Act: -0.0000

Data Index: 1184128 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.2863. Min Act: -0.0000

Data Index: 1602756 (Python Code)

Max Activating Token Index: 205

Text #7

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.2908. Min Act: -0.0000

Data Index: 1342571 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.2712. Min Act: -0.0000

Data Index: 1142347 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.2745. Min Act: -0.0000

Data Index: 1591402 (Python Code)

Max Activating Token Index: 589

Text #10

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.2742. Min Act: -0.0000

Data Index: 1461021 (Python Code)

Max Activating Token Index: 432

Text #11

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.2555. Min Act: -0.0000

Data Index: 1615611 (Python Code)

Max Activating Token Index: 331

Text #12

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.2917. Min Act: -0.0001

Data Index: 1367240 (Python Code)

Max Activating Token Index: 453

Text #13

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.2728. Min Act: -0.0000

Data Index: 659859 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.2760. Min Act: -0.0000

Data Index: 436311 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.2630. Min Act: -0.0000

Data Index: 219770 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.2655. Min Act: -0.0000

Data Index: 36141 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.2513. Min Act: -0.0000

Data Index: 1031765 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.2623. Min Act: -0.0000

Data Index: 115269 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.2576. Min Act: -0.0000

Data Index: 1561387 (Python Code)

Max Activating Token Index: 795