Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2333 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0525. Min Act: -0.0002

Data Index: 621854 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0499. Min Act: -0.0002

Data Index: 199998 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0510. Min Act: -0.0002

Data Index: 355560 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0524. Min Act: -0.0002

Data Index: 33600 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1115613 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0503. Min Act: -0.0002

Data Index: 294097 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1053224 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0464. Min Act: -0.0002

Data Index: 135771 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0452. Min Act: -0.0002

Data Index: 764645 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0452. Min Act: -0.0002

Data Index: 927493 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1235995 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0436. Min Act: -0.0002

Data Index: 110605 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1029149 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0426. Min Act: -0.0002

Data Index: 603428 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1152550 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0428. Min Act: -0.0002

Data Index: 827 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0441. Min Act: -0.0002

Data Index: 917973 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0412. Min Act: -0.0002

Data Index: 807791 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0431. Min Act: -0.0002

Data Index: 444782 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0414. Min Act: -0.0002

Data Index: 951997 (C4 (Web Text))

Max Activating Token Index: 380