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

Dataset: The Pile

Neuron 2534 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.7110. Min Act: -0.0000

Data Index: 1065827 (The Pile)

Max Activating Token Index: 931

Text #1

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1493550 (The Pile)

Max Activating Token Index: 289

Text #2

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.6236. Min Act: -0.0000

Data Index: 615315 (The Pile)

Max Activating Token Index: 48

Text #3

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.6078. Min Act: -0.0000

Data Index: 1559384 (The Pile)

Max Activating Token Index: 533

Text #4

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1435592 (The Pile)

Max Activating Token Index: 459

Text #5

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.6031. Min Act: -0.0000

Data Index: 343854 (The Pile)

Max Activating Token Index: 172

Text #6

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5217. Min Act: -0.0000

Data Index: 931818 (The Pile)

Max Activating Token Index: 425

Text #7

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5966. Min Act: -0.0000

Data Index: 1480675 (The Pile)

Max Activating Token Index: 22

Text #8

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5352. Min Act: -0.0000

Data Index: 1341602 (The Pile)

Max Activating Token Index: 588

Text #9

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5719. Min Act: -0.0000

Data Index: 350817 (The Pile)

Max Activating Token Index: 374

Text #10

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5334. Min Act: -0.0000

Data Index: 1429152 (The Pile)

Max Activating Token Index: 254

Text #11

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5643. Min Act: -0.0000

Data Index: 272854 (The Pile)

Max Activating Token Index: 258

Text #12

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1520946 (The Pile)

Max Activating Token Index: 410

Text #13

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1502564 (The Pile)

Max Activating Token Index: 98

Text #14

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1575947 (The Pile)

Max Activating Token Index: 76

Text #15

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1670531 (The Pile)

Max Activating Token Index: 965

Text #16

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5273. Min Act: -0.0000

Data Index: 629023 (The Pile)

Max Activating Token Index: 476

Text #17

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1400130 (The Pile)

Max Activating Token Index: 732

Text #18

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5182. Min Act: -0.0000

Data Index: 1982482 (The Pile)

Max Activating Token Index: 630

Text #19

Max Range: 0.7110. Min Range: -0.7110

Max Act: 0.5329. Min Act: -0.0000

Data Index: 916505 (The Pile)

Max Activating Token Index: 403