Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1124 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3341. Min Act: -0.0000

Data Index: 421165 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3001. Min Act: -0.0000

Data Index: 341672 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3001. Min Act: -0.0000

Data Index: 732893 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2754. Min Act: -0.0000

Data Index: 391960 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2475. Min Act: -0.0000

Data Index: 1073990 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2548. Min Act: -0.0000

Data Index: 326667 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2617. Min Act: -0.0000

Data Index: 263298 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2559. Min Act: -0.0000

Data Index: 383597 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2458. Min Act: -0.0000

Data Index: 130470 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2462. Min Act: -0.0000

Data Index: 8446 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2448. Min Act: -0.0000

Data Index: 332272 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2267. Min Act: -0.0000

Data Index: 347946 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2356. Min Act: -0.0000

Data Index: 688094 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2249. Min Act: -0.0000

Data Index: 200344 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2316. Min Act: -0.0000

Data Index: 246258 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2285. Min Act: -0.0000

Data Index: 196284 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2301. Min Act: -0.0000

Data Index: 74605 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2356. Min Act: -0.0000

Data Index: 644734 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2323. Min Act: -0.0000

Data Index: 925657 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2243. Min Act: -0.0000

Data Index: 320982 (C4 (Web Text))

Max Activating Token Index: 992