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

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

Neuron 5352 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: 0.0554. Min Range: -0.0554

Max Act: 0.0554. Min Act: -0.0002

Data Index: 1002439 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1024958 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0368. Min Act: -0.0002

Data Index: 396127 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0358. Min Act: -0.0002

Data Index: 843714 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0346. Min Act: -0.0002

Data Index: 214063 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0357. Min Act: -0.0002

Data Index: 651227 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0348. Min Act: -0.0002

Data Index: 546473 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1124070 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1174815 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0358. Min Act: -0.0002

Data Index: 877156 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1323652 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0319. Min Act: -0.0002

Data Index: 240412 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0316. Min Act: -0.0002

Data Index: 643086 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0322. Min Act: -0.0002

Data Index: 735228 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0322. Min Act: -0.0002

Data Index: 32689 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0331. Min Act: -0.0002

Data Index: 362201 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0300. Min Act: -0.0002

Data Index: 591254 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0303. Min Act: -0.0002

Data Index: 158879 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1222057 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.0554. Min Range: -0.0554

Max Act: 0.0303. Min Act: -0.0002

Data Index: 367534 (C4 (Web Text))

Max Activating Token Index: 534