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

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

Neuron 4565 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2655. Min Range: -5.2655

Max Act: 5.2655. Min Act: -0.0000

Data Index: 1549504 (Python Code)

Max Activating Token Index: 32

Text #1

Max Range: 5.2655. Min Range: -5.2655

Max Act: 5.0659. Min Act: -0.0000

Data Index: 1389087 (Python Code)

Max Activating Token Index: 161

Text #2

Max Range: 5.2655. Min Range: -5.2655

Max Act: 4.6568. Min Act: -0.0000

Data Index: 1460408 (Python Code)

Max Activating Token Index: 99

Text #3

Max Range: 5.2655. Min Range: -5.2655

Max Act: 4.0725. Min Act: -0.0000

Data Index: 1574129 (Python Code)

Max Activating Token Index: 296

Text #4

Max Range: 5.2655. Min Range: -5.2655

Max Act: 4.4332. Min Act: -0.0000

Data Index: 1533266 (Python Code)

Max Activating Token Index: 323

Text #5

Max Range: 5.2655. Min Range: -5.2655

Max Act: 3.9880. Min Act: -0.0000

Data Index: 1649956 (Python Code)

Max Activating Token Index: 659

Text #6

Max Range: 5.2655. Min Range: -5.2655

Max Act: 4.3214. Min Act: -0.0000

Data Index: 1441020 (Python Code)

Max Activating Token Index: 157

Text #7

Max Range: 5.2655. Min Range: -5.2655

Max Act: 4.3338. Min Act: -0.0000

Data Index: 1388670 (Python Code)

Max Activating Token Index: 276

Text #8

Max Range: 5.2655. Min Range: -5.2655

Max Act: 4.5333. Min Act: -0.0000

Data Index: 1417126 (Python Code)

Max Activating Token Index: 248

Text #9

Max Range: 5.2655. Min Range: -5.2655

Max Act: 4.1477. Min Act: -0.0000

Data Index: 1607536 (Python Code)

Max Activating Token Index: 603

Text #10

Max Range: 5.2655. Min Range: -5.2655

Max Act: 4.2866. Min Act: -0.0000

Data Index: 1392340 (Python Code)

Max Activating Token Index: 537

Text #11

Max Range: 5.2655. Min Range: -5.2655

Max Act: 3.9623. Min Act: -0.0000

Data Index: 1504913 (Python Code)

Max Activating Token Index: 81

Text #12

Max Range: 5.2655. Min Range: -5.2655

Max Act: 4.6120. Min Act: -0.0000

Data Index: 1420095 (Python Code)

Max Activating Token Index: 252

Text #13

Max Range: 5.2655. Min Range: -5.2655

Max Act: 3.7222. Min Act: -0.0000

Data Index: 1555504 (Python Code)

Max Activating Token Index: 799

Text #14

Max Range: 5.2655. Min Range: -5.2655

Max Act: 3.3749. Min Act: -0.0000

Data Index: 1437280 (Python Code)

Max Activating Token Index: 845

Text #15

Max Range: 5.2655. Min Range: -5.2655

Max Act: 3.8600. Min Act: -0.0000

Data Index: 109822 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 5.2655. Min Range: -5.2655

Max Act: 3.6318. Min Act: -0.0000

Data Index: 1407253 (Python Code)

Max Activating Token Index: 764

Text #17

Max Range: 5.2655. Min Range: -5.2655

Max Act: 3.3986. Min Act: -0.0000

Data Index: 1512470 (Python Code)

Max Activating Token Index: 165

Text #18

Max Range: 5.2655. Min Range: -5.2655

Max Act: 3.3319. Min Act: -0.0000

Data Index: 1627900 (Python Code)

Max Activating Token Index: 635

Text #19

Max Range: 5.2655. Min Range: -5.2655

Max Act: 3.2942. Min Act: -0.0000

Data Index: 1429081 (Python Code)

Max Activating Token Index: 471