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

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

Neuron 0 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: 0.0542. Min Range: -0.0542

Max Act: 0.0470. Min Act: -0.0000

Data Index: 1096234 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0530. Min Act: -0.0000

Data Index: 967935 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0527. Min Act: -0.0000

Data Index: 159356 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0464. Min Act: -0.0000

Data Index: 335902 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0450. Min Act: -0.0000

Data Index: 443894 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0481. Min Act: -0.0000

Data Index: 1295281 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0479. Min Act: -0.0000

Data Index: 691054 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0462. Min Act: -0.0000

Data Index: 501283 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0471. Min Act: -0.0000

Data Index: 30943 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0360. Min Act: -0.0000

Data Index: 1530653 (Python Code)

Max Activating Token Index: 573

Text #10

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0374. Min Act: -0.0000

Data Index: 703580 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0437. Min Act: -0.0000

Data Index: 382821 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0377. Min Act: -0.0000

Data Index: 1338943 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0405. Min Act: -0.0000

Data Index: 739074 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0404. Min Act: -0.0000

Data Index: 29602 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0542. Min Act: -0.0000

Data Index: 310758 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0393. Min Act: -0.0000

Data Index: 1168438 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0329. Min Act: -0.0000

Data Index: 783452 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0382. Min Act: -0.0000

Data Index: 1334529 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0368. Min Act: -0.0000

Data Index: 1142406 (C4 (Web Text))

Max Activating Token Index: 516