Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2542 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0252. Min Act: -0.0004

Data Index: 106315 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0275. Min Act: -0.0004

Data Index: 49725 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0265. Min Act: -0.0004

Data Index: 196370 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0256. Min Act: -0.0004

Data Index: 1074122 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0258. Min Act: -0.0004

Data Index: 662100 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0255. Min Act: -0.0004

Data Index: 858633 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0247. Min Act: -0.0004

Data Index: 269171 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0253. Min Act: -0.0004

Data Index: 365544 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0246. Min Act: -0.0004

Data Index: 754883 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0247. Min Act: -0.0004

Data Index: 318656 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0240. Min Act: -0.0004

Data Index: 1076546 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0243. Min Act: -0.0004

Data Index: 378310 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0243. Min Act: -0.0004

Data Index: 1173091 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0240. Min Act: -0.0004

Data Index: 323009 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0234. Min Act: -0.0004

Data Index: 799 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0229. Min Act: -0.0004

Data Index: 482003 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0239. Min Act: -0.0004

Data Index: 155024 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0243. Min Act: -0.0004

Data Index: 722129 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0238. Min Act: -0.0004

Data Index: 1407200 (Python Code)

Max Activating Token Index: 301

Text #19

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0232. Min Act: -0.0004

Data Index: 213159 (C4 (Web Text))

Max Activating Token Index: 88