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

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

Neuron 3993 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: 0.3985. Min Range: -0.3985

Max Act: 0.3985. Min Act: -0.0000

Data Index: 1252609 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.2854. Min Act: -0.0000

Data Index: 1302486 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.2719. Min Act: 0.0000

Data Index: 621826 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.2665. Min Act: -0.0001

Data Index: 513634 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.2647. Min Act: -0.0001

Data Index: 1270488 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.2654. Min Act: -0.0000

Data Index: 59161 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.2704. Min Act: -0.0000

Data Index: 978538 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.2638. Min Act: -0.0000

Data Index: 58798 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.2597. Min Act: -0.0000

Data Index: 1343910 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.2570. Min Act: -0.0001

Data Index: 114171 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.2570. Min Act: 0.0000

Data Index: 386899 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1040255 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.2607. Min Act: -0.0000

Data Index: 921165 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1249093 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.2344. Min Act: -0.0001

Data Index: 180011 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.2390. Min Act: -0.0001

Data Index: 1356008 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.2380. Min Act: 0.0000

Data Index: 1044429 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.2354. Min Act: -0.0000

Data Index: 416150 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.2186. Min Act: -0.0001

Data Index: 850764 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.3985. Min Range: -0.3985

Max Act: 0.2336. Min Act: -0.0001

Data Index: 1105273 (C4 (Web Text))

Max Activating Token Index: 918