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

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

Neuron 3872 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.8431. Min Act: -0.0000

Data Index: 1438268 (Python Code)

Max Activating Token Index: 346

Text #1

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.6448. Min Act: -0.0000

Data Index: 1612542 (Python Code)

Max Activating Token Index: 430

Text #2

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.5971. Min Act: -0.0000

Data Index: 1486856 (Python Code)

Max Activating Token Index: 578

Text #3

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.4482. Min Act: -0.0000

Data Index: 1632176 (Python Code)

Max Activating Token Index: 834

Text #4

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.2774. Min Act: -0.0000

Data Index: 1401925 (Python Code)

Max Activating Token Index: 888

Text #5

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.4185. Min Act: -0.0000

Data Index: 1367051 (Python Code)

Max Activating Token Index: 954

Text #6

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.3614. Min Act: -0.0000

Data Index: 1381260 (Python Code)

Max Activating Token Index: 520

Text #7

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.2632. Min Act: -0.0000

Data Index: 1560181 (Python Code)

Max Activating Token Index: 776

Text #8

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.3622. Min Act: -0.0000

Data Index: 1617759 (Python Code)

Max Activating Token Index: 748

Text #9

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.4315. Min Act: -0.0000

Data Index: 1438419 (Python Code)

Max Activating Token Index: 907

Text #10

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.2555. Min Act: -0.0000

Data Index: 1462206 (Python Code)

Max Activating Token Index: 731

Text #11

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.3077. Min Act: -0.0000

Data Index: 1543395 (Python Code)

Max Activating Token Index: 654

Text #12

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.3883. Min Act: -0.0000

Data Index: 1476915 (Python Code)

Max Activating Token Index: 682

Text #13

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.3950. Min Act: -0.0000

Data Index: 1495235 (Python Code)

Max Activating Token Index: 652

Text #14

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.3280. Min Act: -0.0000

Data Index: 1375948 (Python Code)

Max Activating Token Index: 906

Text #15

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.3131. Min Act: -0.0000

Data Index: 1576275 (Python Code)

Max Activating Token Index: 355

Text #16

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.2813. Min Act: -0.0000

Data Index: 1511259 (Python Code)

Max Activating Token Index: 148

Text #17

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.2651. Min Act: -0.0000

Data Index: 1616769 (Python Code)

Max Activating Token Index: 1011

Text #18

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.3510. Min Act: -0.0000

Data Index: 1464120 (Python Code)

Max Activating Token Index: 537

Text #19

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.2061. Min Act: -0.0000

Data Index: 1586619 (Python Code)

Max Activating Token Index: 323