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

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

Neuron 212 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8227. Min Range: -5.8227

Max Act: 5.8227. Min Act: -0.0000

Data Index: 305293 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 5.8227. Min Range: -5.8227

Max Act: 5.7622. Min Act: -0.0000

Data Index: 1354118 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 5.8227. Min Range: -5.8227

Max Act: 5.7619. Min Act: -0.0000

Data Index: 8058 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 5.8227. Min Range: -5.8227

Max Act: 5.0366. Min Act: -0.0000

Data Index: 725126 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 5.8227. Min Range: -5.8227

Max Act: 4.7746. Min Act: -0.0000

Data Index: 1221800 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 5.8227. Min Range: -5.8227

Max Act: 4.3245. Min Act: -0.0000

Data Index: 651021 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 5.8227. Min Range: -5.8227

Max Act: 4.3945. Min Act: -0.0000

Data Index: 403646 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 5.8227. Min Range: -5.8227

Max Act: 4.2104. Min Act: -0.0000

Data Index: 1585991 (Python Code)

Max Activating Token Index: 409

Text #8

Max Range: 5.8227. Min Range: -5.8227

Max Act: 4.7234. Min Act: -0.0000

Data Index: 923494 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 5.8227. Min Range: -5.8227

Max Act: 4.3583. Min Act: -0.0000

Data Index: 1430360 (Python Code)

Max Activating Token Index: 818

Text #10

Max Range: 5.8227. Min Range: -5.8227

Max Act: 4.3450. Min Act: -0.0000

Data Index: 521996 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 5.8227. Min Range: -5.8227

Max Act: 4.2227. Min Act: -0.0000

Data Index: 529065 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 5.8227. Min Range: -5.8227

Max Act: 4.3145. Min Act: -0.0000

Data Index: 1454906 (Python Code)

Max Activating Token Index: 857

Text #13

Max Range: 5.8227. Min Range: -5.8227

Max Act: 4.3231. Min Act: -0.0000

Data Index: 913354 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 5.8227. Min Range: -5.8227

Max Act: 4.2987. Min Act: -0.0000

Data Index: 97516 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 5.8227. Min Range: -5.8227

Max Act: 3.7171. Min Act: -0.0000

Data Index: 1144617 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 5.8227. Min Range: -5.8227

Max Act: 4.1425. Min Act: -0.0000

Data Index: 1497575 (Python Code)

Max Activating Token Index: 692

Text #17

Max Range: 5.8227. Min Range: -5.8227

Max Act: 3.4026. Min Act: -0.0000

Data Index: 1394185 (Python Code)

Max Activating Token Index: 913

Text #18

Max Range: 5.8227. Min Range: -5.8227

Max Act: 3.7491. Min Act: -0.0000

Data Index: 1390952 (Python Code)

Max Activating Token Index: 974

Text #19

Max Range: 5.8227. Min Range: -5.8227

Max Act: 3.2127. Min Act: -0.0000

Data Index: 1639642 (Python Code)

Max Activating Token Index: 424