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

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

Neuron 5217 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2448. Min Range: -1.2448

Max Act: 1.2448. Min Act: -0.0000

Data Index: 204401 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 1.2448. Min Range: -1.2448

Max Act: 1.0374. Min Act: -0.0000

Data Index: 925046 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 1.2448. Min Range: -1.2448

Max Act: 1.0623. Min Act: -0.0000

Data Index: 227058 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 1.2448. Min Range: -1.2448

Max Act: 1.0163. Min Act: -0.0000

Data Index: 1642834 (Python Code)

Max Activating Token Index: 936

Text #4

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.8860. Min Act: -0.0000

Data Index: 1014260 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.8858. Min Act: -0.0000

Data Index: 1444610 (Python Code)

Max Activating Token Index: 904

Text #6

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.9408. Min Act: -0.0000

Data Index: 1492016 (Python Code)

Max Activating Token Index: 873

Text #7

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.8941. Min Act: -0.0000

Data Index: 1487242 (Python Code)

Max Activating Token Index: 72

Text #8

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1619705 (Python Code)

Max Activating Token Index: 117

Text #9

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.8772. Min Act: -0.0000

Data Index: 1546930 (Python Code)

Max Activating Token Index: 695

Text #10

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.9272. Min Act: -0.0000

Data Index: 1241196 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.8349. Min Act: -0.0000

Data Index: 1484664 (Python Code)

Max Activating Token Index: 99

Text #12

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.8638. Min Act: -0.0000

Data Index: 1496304 (Python Code)

Max Activating Token Index: 765

Text #13

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.9281. Min Act: -0.0000

Data Index: 248172 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.8761. Min Act: -0.0000

Data Index: 1432192 (Python Code)

Max Activating Token Index: 61

Text #15

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.8384. Min Act: -0.0000

Data Index: 1454405 (Python Code)

Max Activating Token Index: 738

Text #16

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1459178 (Python Code)

Max Activating Token Index: 609

Text #17

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.8383. Min Act: -0.0000

Data Index: 169472 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.8390. Min Act: -0.0000

Data Index: 1407659 (Python Code)

Max Activating Token Index: 511

Text #19

Max Range: 1.2448. Min Range: -1.2448

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1638470 (Python Code)

Max Activating Token Index: 750