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

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

Neuron 2501 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: 0.9154. Min Range: -0.9154

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1098408 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 0.9154. Min Range: -0.9154

Max Act: 0.7624. Min Act: -0.0000

Data Index: 516692 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 0.9154. Min Range: -0.9154

Max Act: 0.6966. Min Act: -0.0000

Data Index: 777781 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.9154. Min Range: -0.9154

Max Act: 0.7409. Min Act: -0.0000

Data Index: 378086 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 0.9154. Min Range: -0.9154

Max Act: 0.6959. Min Act: -0.0000

Data Index: 513554 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.9154. Min Range: -0.9154

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1288097 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.9154. Min Range: -0.9154

Max Act: 0.6819. Min Act: -0.0000

Data Index: 756084 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.9154. Min Range: -0.9154

Max Act: 0.6896. Min Act: -0.0000

Data Index: 1135964 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 0.9154. Min Range: -0.9154

Max Act: 0.6839. Min Act: -0.0000

Data Index: 422871 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 0.9154. Min Range: -0.9154

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1396861 (Python Code)

Max Activating Token Index: 635

Text #10

Max Range: 0.9154. Min Range: -0.9154

Max Act: 0.6227. Min Act: -0.0000

Data Index: 632462 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 0.9154. Min Range: -0.9154

Max Act: 0.5431. Min Act: -0.0000

Data Index: 1177845 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 0.9154. Min Range: -0.9154

Max Act: 0.6132. Min Act: -0.0000

Data Index: 579193 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.9154. Min Range: -0.9154

Max Act: 0.6397. Min Act: -0.0000

Data Index: 1365765 (Python Code)

Max Activating Token Index: 796

Text #14

Max Range: 0.9154. Min Range: -0.9154

Max Act: 0.6008. Min Act: -0.0000

Data Index: 868413 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.9154. Min Range: -0.9154

Max Act: 0.5606. Min Act: -0.0000

Data Index: 481103 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.9154. Min Range: -0.9154

Max Act: 0.6007. Min Act: -0.0000

Data Index: 1556689 (Python Code)

Max Activating Token Index: 998

Text #17

Max Range: 0.9154. Min Range: -0.9154

Max Act: 0.5911. Min Act: -0.0000

Data Index: 706268 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.9154. Min Range: -0.9154

Max Act: 0.4942. Min Act: -0.0000

Data Index: 98553 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.9154. Min Range: -0.9154

Max Act: 0.5580. Min Act: -0.0000

Data Index: 346749 (C4 (Web Text))

Max Activating Token Index: 288