Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1734 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.7179. Min Range: -3.7179

Max Act: 3.7179. Min Act: -0.0000

Data Index: 1418054 (Python Code)

Max Activating Token Index: 810

Text #1

Max Range: 3.7179. Min Range: -3.7179

Max Act: 3.3148. Min Act: -0.0000

Data Index: 1507224 (Python Code)

Max Activating Token Index: 738

Text #2

Max Range: 3.7179. Min Range: -3.7179

Max Act: 3.1084. Min Act: -0.0000

Data Index: 1458484 (Python Code)

Max Activating Token Index: 850

Text #3

Max Range: 3.7179. Min Range: -3.7179

Max Act: 3.1270. Min Act: -0.0000

Data Index: 1432695 (Python Code)

Max Activating Token Index: 638

Text #4

Max Range: 3.7179. Min Range: -3.7179

Max Act: 3.5202. Min Act: -0.0000

Data Index: 1466462 (Python Code)

Max Activating Token Index: 618

Text #5

Max Range: 3.7179. Min Range: -3.7179

Max Act: 2.8412. Min Act: -0.0000

Data Index: 659279 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 3.7179. Min Range: -3.7179

Max Act: 3.0951. Min Act: -0.0000

Data Index: 557953 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 3.7179. Min Range: -3.7179

Max Act: 2.4450. Min Act: -0.0000

Data Index: 1425078 (Python Code)

Max Activating Token Index: 662

Text #8

Max Range: 3.7179. Min Range: -3.7179

Max Act: 2.6159. Min Act: -0.0000

Data Index: 422418 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 3.7179. Min Range: -3.7179

Max Act: 2.5498. Min Act: -0.0000

Data Index: 652618 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 3.7179. Min Range: -3.7179

Max Act: 2.4321. Min Act: -0.0000

Data Index: 1152955 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 3.7179. Min Range: -3.7179

Max Act: 2.3901. Min Act: -0.0000

Data Index: 1408540 (Python Code)

Max Activating Token Index: 729

Text #12

Max Range: 3.7179. Min Range: -3.7179

Max Act: 2.5389. Min Act: -0.0000

Data Index: 1655721 (Python Code)

Max Activating Token Index: 396

Text #13

Max Range: 3.7179. Min Range: -3.7179

Max Act: 2.2592. Min Act: -0.0000

Data Index: 1165531 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 3.7179. Min Range: -3.7179

Max Act: 2.0900. Min Act: -0.0000

Data Index: 774631 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 3.7179. Min Range: -3.7179

Max Act: 1.9865. Min Act: -0.0000

Data Index: 302141 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 3.7179. Min Range: -3.7179

Max Act: 2.2204. Min Act: -0.0000

Data Index: 387727 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 3.7179. Min Range: -3.7179

Max Act: 2.3708. Min Act: -0.0000

Data Index: 1461058 (Python Code)

Max Activating Token Index: 614

Text #18

Max Range: 3.7179. Min Range: -3.7179

Max Act: 2.1002. Min Act: -0.0000

Data Index: 1651021 (Python Code)

Max Activating Token Index: 354

Text #19

Max Range: 3.7179. Min Range: -3.7179

Max Act: 2.0793. Min Act: -0.0000

Data Index: 1026261 (C4 (Web Text))

Max Activating Token Index: 187