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

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

Neuron 1837 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1399. Min Range: -2.1399

Max Act: 2.0953. Min Act: -0.0000

Data Index: 399588 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 2.1399. Min Range: -2.1399

Max Act: 2.1399. Min Act: -0.0000

Data Index: 302249 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 2.1399. Min Range: -2.1399

Max Act: 1.9157. Min Act: -0.0000

Data Index: 2671 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 2.1399. Min Range: -2.1399

Max Act: 1.5895. Min Act: -0.0000

Data Index: 1473924 (Python Code)

Max Activating Token Index: 371

Text #4

Max Range: 2.1399. Min Range: -2.1399

Max Act: 1.5420. Min Act: -0.0000

Data Index: 1578768 (Python Code)

Max Activating Token Index: 145

Text #5

Max Range: 2.1399. Min Range: -2.1399

Max Act: 1.5886. Min Act: -0.0000

Data Index: 1387494 (Python Code)

Max Activating Token Index: 71

Text #6

Max Range: 2.1399. Min Range: -2.1399

Max Act: 1.5382. Min Act: -0.0000

Data Index: 1605504 (Python Code)

Max Activating Token Index: 64

Text #7

Max Range: 2.1399. Min Range: -2.1399

Max Act: 1.4736. Min Act: -0.0000

Data Index: 1507653 (Python Code)

Max Activating Token Index: 660

Text #8

Max Range: 2.1399. Min Range: -2.1399

Max Act: 1.4655. Min Act: -0.0000

Data Index: 1492081 (Python Code)

Max Activating Token Index: 384

Text #9

Max Range: 2.1399. Min Range: -2.1399

Max Act: 1.5328. Min Act: -0.0000

Data Index: 1362142 (Python Code)

Max Activating Token Index: 930

Text #10

Max Range: 2.1399. Min Range: -2.1399

Max Act: 1.4773. Min Act: -0.0000

Data Index: 1378563 (Python Code)

Max Activating Token Index: 108

Text #11

Max Range: 2.1399. Min Range: -2.1399

Max Act: 1.4654. Min Act: -0.0000

Data Index: 1517412 (Python Code)

Max Activating Token Index: 123

Text #12

Max Range: 2.1399. Min Range: -2.1399

Max Act: 1.4459. Min Act: -0.0000

Data Index: 1464357 (Python Code)

Max Activating Token Index: 954

Text #13

Max Range: 2.1399. Min Range: -2.1399

Max Act: 1.3950. Min Act: -0.0000

Data Index: 451928 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 2.1399. Min Range: -2.1399

Max Act: 1.3607. Min Act: -0.0000

Data Index: 44874 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 2.1399. Min Range: -2.1399

Max Act: 1.4450. Min Act: -0.0000

Data Index: 1403393 (Python Code)

Max Activating Token Index: 643

Text #16

Max Range: 2.1399. Min Range: -2.1399

Max Act: 1.4440. Min Act: -0.0000

Data Index: 1485293 (Python Code)

Max Activating Token Index: 762

Text #17

Max Range: 2.1399. Min Range: -2.1399

Max Act: 1.3349. Min Act: -0.0000

Data Index: 205844 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 2.1399. Min Range: -2.1399

Max Act: 1.3990. Min Act: -0.0000

Data Index: 1445856 (Python Code)

Max Activating Token Index: 513

Text #19

Max Range: 2.1399. Min Range: -2.1399

Max Act: 1.4667. Min Act: -0.0000

Data Index: 1482617 (Python Code)

Max Activating Token Index: 856