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

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

Neuron 306 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: 0.0428. Min Range: -0.0428

Max Act: 0.0428. Min Act: -0.0004

Data Index: 1210054 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0413. Min Act: -0.0004

Data Index: 1067073 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0404. Min Act: -0.0004

Data Index: 640711 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0414. Min Act: -0.0004

Data Index: 66113 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0404. Min Act: -0.0004

Data Index: 437424 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0421. Min Act: -0.0004

Data Index: 312281 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0405. Min Act: -0.0004

Data Index: 970605 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0409. Min Act: -0.0004

Data Index: 591056 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0418. Min Act: -0.0004

Data Index: 851828 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0378. Min Act: -0.0004

Data Index: 335206 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0386. Min Act: -0.0004

Data Index: 1011155 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0384. Min Act: -0.0004

Data Index: 49763 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0391. Min Act: -0.0004

Data Index: 216713 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0368. Min Act: -0.0004

Data Index: 65464 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0367. Min Act: -0.0004

Data Index: 666104 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0358. Min Act: -0.0004

Data Index: 861163 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0404. Min Act: -0.0004

Data Index: 1632410 (Python Code)

Max Activating Token Index: 501

Text #17

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0351. Min Act: -0.0004

Data Index: 609476 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0386. Min Act: -0.0004

Data Index: 1101390 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0414. Min Act: -0.0004

Data Index: 684229 (C4 (Web Text))

Max Activating Token Index: 696