Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 192 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0374. Min Act: -0.0002

Data Index: 870985 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0354. Min Act: -0.0002

Data Index: 645929 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0338. Min Act: -0.0002

Data Index: 654416 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1180992 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0332. Min Act: -0.0002

Data Index: 484492 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1245274 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0307. Min Act: -0.0002

Data Index: 443957 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0301. Min Act: -0.0002

Data Index: 802667 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0298. Min Act: -0.0002

Data Index: 113693 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0293. Min Act: -0.0002

Data Index: 175122 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0281. Min Act: -0.0002

Data Index: 731108 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1560235 (Python Code)

Max Activating Token Index: 921

Text #12

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0281. Min Act: -0.0002

Data Index: 802768 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0283. Min Act: -0.0002

Data Index: 279671 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0278. Min Act: -0.0002

Data Index: 878429 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1068839 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0260. Min Act: -0.0002

Data Index: 929923 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0256. Min Act: -0.0002

Data Index: 409819 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0267. Min Act: -0.0002

Data Index: 300378 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1575689 (Python Code)

Max Activating Token Index: 67