Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 259 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0486. Min Act: -0.0006

Data Index: 869536 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0473. Min Act: -0.0006

Data Index: 266785 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0461. Min Act: -0.0006

Data Index: 1330726 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0450. Min Act: -0.0006

Data Index: 554536 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0465. Min Act: -0.0006

Data Index: 539781 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0477. Min Act: -0.0006

Data Index: 381271 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0454. Min Act: -0.0006

Data Index: 207660 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0454. Min Act: -0.0006

Data Index: 924368 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0462. Min Act: -0.0006

Data Index: 36138 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0451. Min Act: -0.0006

Data Index: 5944 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0454. Min Act: -0.0006

Data Index: 1292582 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0449. Min Act: -0.0006

Data Index: 708095 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0454. Min Act: -0.0006

Data Index: 235554 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0452. Min Act: -0.0006

Data Index: 130271 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0463. Min Act: -0.0006

Data Index: 1033711 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0457. Min Act: -0.0006

Data Index: 1178921 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0438. Min Act: -0.0006

Data Index: 1067000 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0454. Min Act: -0.0006

Data Index: 1144318 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0446. Min Act: -0.0006

Data Index: 1333080 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0448. Min Act: -0.0006

Data Index: 496801 (C4 (Web Text))

Max Activating Token Index: 494