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

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

Neuron 4023 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: 2.5818. Min Range: -2.5818

Max Act: 2.5818. Min Act: -0.0000

Data Index: 1643018 (Python Code)

Max Activating Token Index: 775

Text #1

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.4115. Min Act: -0.0000

Data Index: 1567844 (Python Code)

Max Activating Token Index: 251

Text #2

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.3786. Min Act: -0.0000

Data Index: 1435479 (Python Code)

Max Activating Token Index: 167

Text #3

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.3649. Min Act: -0.0000

Data Index: 1573368 (Python Code)

Max Activating Token Index: 217

Text #4

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.3243. Min Act: -0.0000

Data Index: 1651587 (Python Code)

Max Activating Token Index: 348

Text #5

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.4367. Min Act: -0.0000

Data Index: 1594664 (Python Code)

Max Activating Token Index: 910

Text #6

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.4139. Min Act: -0.0000

Data Index: 1429981 (Python Code)

Max Activating Token Index: 843

Text #7

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.2498. Min Act: -0.0000

Data Index: 1385107 (Python Code)

Max Activating Token Index: 67

Text #8

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.2528. Min Act: -0.0000

Data Index: 1421066 (Python Code)

Max Activating Token Index: 927

Text #9

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.3532. Min Act: -0.0000

Data Index: 1415516 (Python Code)

Max Activating Token Index: 22

Text #10

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.0856. Min Act: -0.0000

Data Index: 58035 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 2.5818. Min Range: -2.5818

Max Act: 1.9419. Min Act: -0.0000

Data Index: 1437419 (Python Code)

Max Activating Token Index: 214

Text #12

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.1482. Min Act: -0.0000

Data Index: 1416994 (Python Code)

Max Activating Token Index: 222

Text #13

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.2270. Min Act: -0.0000

Data Index: 1522205 (Python Code)

Max Activating Token Index: 991

Text #14

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.0703. Min Act: -0.0000

Data Index: 343445 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.0788. Min Act: -0.0000

Data Index: 1586872 (Python Code)

Max Activating Token Index: 608

Text #16

Max Range: 2.5818. Min Range: -2.5818

Max Act: 1.9691. Min Act: -0.0000

Data Index: 1447675 (Python Code)

Max Activating Token Index: 154

Text #17

Max Range: 2.5818. Min Range: -2.5818

Max Act: 1.9486. Min Act: -0.0000

Data Index: 1631208 (Python Code)

Max Activating Token Index: 259

Text #18

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.0559. Min Act: -0.0000

Data Index: 1585017 (Python Code)

Max Activating Token Index: 659

Text #19

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.0390. Min Act: -0.0000

Data Index: 1532200 (Python Code)

Max Activating Token Index: 581