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

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

Neuron 4649 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4978. Min Act: -0.0000

Data Index: 1378853 (Python Code)

Max Activating Token Index: 666

Text #1

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4859. Min Act: -0.0000

Data Index: 1495355 (Python Code)

Max Activating Token Index: 647

Text #2

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4084. Min Act: -0.0000

Data Index: 1646368 (Python Code)

Max Activating Token Index: 307

Text #3

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1380933 (Python Code)

Max Activating Token Index: 522

Text #4

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3230. Min Act: -0.0000

Data Index: 1568324 (Python Code)

Max Activating Token Index: 364

Text #5

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1605844 (Python Code)

Max Activating Token Index: 682

Text #6

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3333. Min Act: -0.0000

Data Index: 1404572 (Python Code)

Max Activating Token Index: 611

Text #7

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1422801 (Python Code)

Max Activating Token Index: 86

Text #8

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1593870 (Python Code)

Max Activating Token Index: 231

Text #9

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3318. Min Act: -0.0000

Data Index: 1558891 (Python Code)

Max Activating Token Index: 510

Text #10

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1380719 (Python Code)

Max Activating Token Index: 918

Text #11

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3216. Min Act: -0.0000

Data Index: 1636483 (Python Code)

Max Activating Token Index: 924

Text #12

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3486. Min Act: -0.0000

Data Index: 1453342 (Python Code)

Max Activating Token Index: 912

Text #13

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3231. Min Act: -0.0000

Data Index: 20039 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3197. Min Act: -0.0000

Data Index: 1637150 (Python Code)

Max Activating Token Index: 192

Text #15

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3395. Min Act: -0.0000

Data Index: 1458012 (Python Code)

Max Activating Token Index: 882

Text #16

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3208. Min Act: -0.0000

Data Index: 1631035 (Python Code)

Max Activating Token Index: 252

Text #17

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.2939. Min Act: -0.0000

Data Index: 1448368 (Python Code)

Max Activating Token Index: 484

Text #18

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.2821. Min Act: -0.0000

Data Index: 1565079 (Python Code)

Max Activating Token Index: 892

Text #19

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1557760 (Python Code)

Max Activating Token Index: 686