Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1467 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0289. Min Act: -0.0006

Data Index: 69913 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0271. Min Act: -0.0006

Data Index: 877407 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0271. Min Act: -0.0006

Data Index: 973430 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0258. Min Act: -0.0006

Data Index: 247611 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0260. Min Act: -0.0006

Data Index: 587909 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0266. Min Act: -0.0006

Data Index: 926424 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0258. Min Act: -0.0006

Data Index: 368539 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0252. Min Act: -0.0005

Data Index: 1378435 (Python Code)

Max Activating Token Index: 809

Text #8

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0256. Min Act: -0.0005

Data Index: 249790 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0251. Min Act: -0.0006

Data Index: 1446534 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1603470 (Python Code)

Max Activating Token Index: 467

Text #11

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0243. Min Act: -0.0006

Data Index: 1583629 (Python Code)

Max Activating Token Index: 968

Text #12

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0248. Min Act: -0.0005

Data Index: 1609782 (Python Code)

Max Activating Token Index: 8

Text #13

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0248. Min Act: -0.0005

Data Index: 1622628 (Python Code)

Max Activating Token Index: 8

Text #14

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0248. Min Act: -0.0005

Data Index: 1381558 (Python Code)

Max Activating Token Index: 8

Text #15

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1453385 (Python Code)

Max Activating Token Index: 429

Text #16

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0246. Min Act: -0.0005

Data Index: 1528732 (Python Code)

Max Activating Token Index: 361

Text #17

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0246. Min Act: -0.0006

Data Index: 1561375 (Python Code)

Max Activating Token Index: 1017

Text #18

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0240. Min Act: -0.0005

Data Index: 1543365 (Python Code)

Max Activating Token Index: 313

Text #19

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0245. Min Act: -0.0006

Data Index: 644409 (C4 (Web Text))

Max Activating Token Index: 229