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

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

Neuron 285 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: 0.2972. Min Range: -0.2972

Max Act: 0.2972. Min Act: -0.0001

Data Index: 1549600 (Python Code)

Max Activating Token Index: 936

Text #1

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2678. Min Act: -0.0001

Data Index: 1448257 (Python Code)

Max Activating Token Index: 36

Text #2

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2503. Min Act: -0.0001

Data Index: 1409349 (Python Code)

Max Activating Token Index: 470

Text #3

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2447. Min Act: -0.0001

Data Index: 1362508 (Python Code)

Max Activating Token Index: 104

Text #4

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2690. Min Act: -0.0001

Data Index: 352638 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2529. Min Act: -0.0001

Data Index: 1611015 (Python Code)

Max Activating Token Index: 159

Text #6

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2412. Min Act: -0.0000

Data Index: 364172 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2426. Min Act: -0.0001

Data Index: 252918 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2506. Min Act: -0.0000

Data Index: 488259 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2368. Min Act: -0.0001

Data Index: 1424167 (Python Code)

Max Activating Token Index: 47

Text #10

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2296. Min Act: -0.0001

Data Index: 116313 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2378. Min Act: -0.0001

Data Index: 1397995 (Python Code)

Max Activating Token Index: 984

Text #12

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2224. Min Act: -0.0001

Data Index: 339358 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2231. Min Act: -0.0001

Data Index: 1220510 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2018. Min Act: -0.0001

Data Index: 1457294 (Python Code)

Max Activating Token Index: 504

Text #15

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2280. Min Act: -0.0001

Data Index: 1615444 (Python Code)

Max Activating Token Index: 279

Text #16

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2120. Min Act: -0.0001

Data Index: 1403116 (Python Code)

Max Activating Token Index: 789

Text #17

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2112. Min Act: -0.0001

Data Index: 1480387 (Python Code)

Max Activating Token Index: 22

Text #18

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2223. Min Act: -0.0000

Data Index: 617620 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2279. Min Act: -0.0001

Data Index: 730244 (C4 (Web Text))

Max Activating Token Index: 295