Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3691 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.3627. Min Act: 0.0000

Data Index: 1476179 (Python Code)

Max Activating Token Index: 226

Text #1

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.5161. Min Act: -0.0000

Data Index: 1546828 (Python Code)

Max Activating Token Index: 770

Text #2

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.3598. Min Act: -0.0000

Data Index: 1636168 (Python Code)

Max Activating Token Index: 878

Text #3

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.4253. Min Act: -0.0000

Data Index: 1529218 (Python Code)

Max Activating Token Index: 557

Text #4

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.3039. Min Act: -0.0000

Data Index: 1436160 (Python Code)

Max Activating Token Index: 261

Text #5

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.2705. Min Act: -0.0000

Data Index: 1417102 (Python Code)

Max Activating Token Index: 963

Text #6

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.2431. Min Act: -0.0001

Data Index: 1560452 (Python Code)

Max Activating Token Index: 46

Text #7

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.3338. Min Act: -0.0001

Data Index: 1625409 (Python Code)

Max Activating Token Index: 748

Text #8

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.2095. Min Act: -0.0000

Data Index: 1637388 (Python Code)

Max Activating Token Index: 325

Text #9

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.3036. Min Act: -0.0000

Data Index: 1600813 (Python Code)

Max Activating Token Index: 996

Text #10

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.9822. Min Act: -0.0000

Data Index: 1384635 (Python Code)

Max Activating Token Index: 571

Text #11

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.1539. Min Act: -0.0000

Data Index: 1586407 (Python Code)

Max Activating Token Index: 960

Text #12

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.0768. Min Act: 0.0000

Data Index: 1586244 (Python Code)

Max Activating Token Index: 705

Text #13

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.0470. Min Act: 0.0000

Data Index: 1634611 (Python Code)

Max Activating Token Index: 983

Text #14

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.9893. Min Act: -0.0000

Data Index: 1583035 (Python Code)

Max Activating Token Index: 937

Text #15

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.0291. Min Act: -0.0000

Data Index: 1437081 (Python Code)

Max Activating Token Index: 729

Text #16

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.9824. Min Act: -0.0000

Data Index: 1391666 (Python Code)

Max Activating Token Index: 638

Text #17

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.9622. Min Act: -0.0000

Data Index: 1439794 (Python Code)

Max Activating Token Index: 343

Text #18

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.0024. Min Act: -0.0000

Data Index: 1504093 (Python Code)

Max Activating Token Index: 216

Text #19

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.9770. Min Act: 0.0000

Data Index: 1625522 (Python Code)

Max Activating Token Index: 386