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

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

Neuron 3773 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.8409. Min Act: -0.0000

Data Index: 717817 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.4378. Min Act: -0.0000

Data Index: 632090 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.2369. Min Act: -0.0000

Data Index: 556731 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.2167. Min Act: -0.0000

Data Index: 459745 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.1585. Min Act: -0.0000

Data Index: 611207 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.1470. Min Act: -0.0000

Data Index: 1240030 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.0394. Min Act: -0.0000

Data Index: 165171 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.0587. Min Act: -0.0000

Data Index: 829438 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.1311. Min Act: -0.0000

Data Index: 1127096 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.0397. Min Act: -0.0000

Data Index: 1286186 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.0244. Min Act: -0.0000

Data Index: 429322 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.0574. Min Act: -0.0000

Data Index: 1067354 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.0382. Min Act: -0.0000

Data Index: 600481 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.0301. Min Act: -0.0000

Data Index: 1046352 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.0416. Min Act: 0.0000

Data Index: 313991 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 1.8409. Min Range: -1.8409

Max Act: 0.9552. Min Act: -0.0000

Data Index: 1308435 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 1.8409. Min Range: -1.8409

Max Act: 1.0048. Min Act: -0.0000

Data Index: 1115008 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 1.8409. Min Range: -1.8409

Max Act: 0.9676. Min Act: -0.0000

Data Index: 115076 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 1.8409. Min Range: -1.8409

Max Act: 0.9461. Min Act: 0.0000

Data Index: 525091 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 1.8409. Min Range: -1.8409

Max Act: 0.9529. Min Act: -0.0000

Data Index: 1113839 (C4 (Web Text))

Max Activating Token Index: 442