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

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

Neuron 2275 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.3451. Min Act: -0.0000

Data Index: 748927 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.3253. Min Act: -0.0000

Data Index: 320207 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.3216. Min Act: -0.0000

Data Index: 40425 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.3003. Min Act: -0.0000

Data Index: 65442 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2965. Min Act: -0.0000

Data Index: 81421 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2688. Min Act: -0.0000

Data Index: 1100302 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2663. Min Act: -0.0000

Data Index: 282339 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1296205 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2463. Min Act: -0.0000

Data Index: 21646 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2462. Min Act: -0.0000

Data Index: 39623 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2453. Min Act: -0.0000

Data Index: 1112419 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2450. Min Act: -0.0000

Data Index: 70453 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2307. Min Act: -0.0000

Data Index: 821545 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2295. Min Act: -0.0000

Data Index: 398585 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2264. Min Act: -0.0000

Data Index: 108778 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1081297 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2340. Min Act: -0.0000

Data Index: 1135050 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2332. Min Act: -0.0000

Data Index: 835783 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2254. Min Act: -0.0000

Data Index: 468652 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 0.3451. Min Range: -0.3451

Max Act: 0.2162. Min Act: -0.0000

Data Index: 88505 (C4 (Web Text))

Max Activating Token Index: 969