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

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

Neuron 3186 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.5768. Min Act: -0.0000

Data Index: 1576590 (Python Code)

Max Activating Token Index: 22

Text #1

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.5382. Min Act: -0.0001

Data Index: 1389359 (Python Code)

Max Activating Token Index: 373

Text #2

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.5212. Min Act: -0.0001

Data Index: 588670 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.5143. Min Act: -0.0000

Data Index: 678360 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.4616. Min Act: -0.0000

Data Index: 6346 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.4835. Min Act: -0.0001

Data Index: 240370 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.4645. Min Act: -0.0000

Data Index: 965991 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.4828. Min Act: -0.0001

Data Index: 995222 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.4585. Min Act: -0.0000

Data Index: 503602 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.4531. Min Act: -0.0001

Data Index: 22517 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.4376. Min Act: -0.0000

Data Index: 186327 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.4367. Min Act: -0.0000

Data Index: 22985 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.4291. Min Act: 0.0000

Data Index: 1583686 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.4432. Min Act: -0.0001

Data Index: 327322 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1039150 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.4195. Min Act: -0.0000

Data Index: 33774 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.4199. Min Act: -0.0000

Data Index: 838243 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.4191. Min Act: 0.0000

Data Index: 997833 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.4167. Min Act: -0.0000

Data Index: 1149268 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.5768. Min Range: -0.5768

Max Act: 0.4151. Min Act: -0.0000

Data Index: 583490 (C4 (Web Text))

Max Activating Token Index: 689