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

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

Neuron 528 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.1028. Min Act: -0.0001

Data Index: 782984 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 1.1028. Min Range: -1.1028

Max Act: 1.0267. Min Act: -0.0001

Data Index: 1013290 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.5751. Min Act: -0.0001

Data Index: 1488191 (Python Code)

Max Activating Token Index: 71

Text #3

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.5523. Min Act: -0.0001

Data Index: 1372319 (Python Code)

Max Activating Token Index: 51

Text #4

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.5091. Min Act: -0.0001

Data Index: 1538430 (Python Code)

Max Activating Token Index: 37

Text #5

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.4243. Min Act: -0.0001

Data Index: 1454102 (Python Code)

Max Activating Token Index: 182

Text #6

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.4088. Min Act: -0.0001

Data Index: 567618 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.4353. Min Act: -0.0001

Data Index: 656401 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.3393. Min Act: -0.0001

Data Index: 1460885 (Python Code)

Max Activating Token Index: 863

Text #9

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.3749. Min Act: -0.0001

Data Index: 427319 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.3752. Min Act: -0.0001

Data Index: 808655 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.3748. Min Act: -0.0001

Data Index: 1484803 (Python Code)

Max Activating Token Index: 51

Text #12

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.3619. Min Act: -0.0001

Data Index: 1646516 (Python Code)

Max Activating Token Index: 42

Text #13

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.3306. Min Act: -0.0001

Data Index: 789607 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.3558. Min Act: -0.0001

Data Index: 1324601 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.3503. Min Act: -0.0001

Data Index: 1094005 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.3501. Min Act: -0.0001

Data Index: 1379704 (Python Code)

Max Activating Token Index: 72

Text #17

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.3354. Min Act: -0.0001

Data Index: 820494 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.3433. Min Act: -0.0001

Data Index: 1649062 (Python Code)

Max Activating Token Index: 147

Text #19

Max Range: 1.1028. Min Range: -1.1028

Max Act: 0.3584. Min Act: -0.0001

Data Index: 145055 (C4 (Web Text))

Max Activating Token Index: 946