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

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

Neuron 692 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: 0.0396. Min Range: -0.0396

Max Act: 0.0396. Min Act: -0.0006

Data Index: 188271 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0365. Min Act: -0.0006

Data Index: 784602 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0353. Min Act: -0.0006

Data Index: 48933 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0349. Min Act: -0.0006

Data Index: 1081168 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0344. Min Act: -0.0006

Data Index: 240453 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0327. Min Act: -0.0006

Data Index: 1231226 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0322. Min Act: -0.0006

Data Index: 305487 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0314. Min Act: -0.0006

Data Index: 1036564 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0311. Min Act: -0.0006

Data Index: 1289583 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0298. Min Act: -0.0006

Data Index: 865576 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0301. Min Act: -0.0006

Data Index: 897358 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0294. Min Act: -0.0006

Data Index: 1503859 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0290. Min Act: -0.0006

Data Index: 949985 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0284. Min Act: -0.0006

Data Index: 1217701 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0282. Min Act: -0.0006

Data Index: 1041401 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0280. Min Act: -0.0006

Data Index: 1344559 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0275. Min Act: -0.0006

Data Index: 1541517 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0276. Min Act: -0.0006

Data Index: 436306 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0271. Min Act: -0.0006

Data Index: 284298 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0270. Min Act: -0.0006

Data Index: 1250334 (C4 (Web Text))

Max Activating Token Index: 1023