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

Dataset: The Pile

Neuron 2786 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: 1.3468. Min Range: -1.3468

Max Act: 1.3444. Min Act: -0.0000

Data Index: 725978 (The Pile)

Max Activating Token Index: 57

Text #1

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.3468. Min Act: -0.0000

Data Index: 1043469 (The Pile)

Max Activating Token Index: 26

Text #2

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.2804. Min Act: -0.0000

Data Index: 1809653 (The Pile)

Max Activating Token Index: 83

Text #3

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.2448. Min Act: -0.0000

Data Index: 752737 (The Pile)

Max Activating Token Index: 826

Text #4

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.2410. Min Act: -0.0000

Data Index: 499282 (The Pile)

Max Activating Token Index: 262

Text #5

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.1207. Min Act: -0.0000

Data Index: 1283207 (The Pile)

Max Activating Token Index: 617

Text #6

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.1765. Min Act: -0.0000

Data Index: 1764430 (The Pile)

Max Activating Token Index: 44

Text #7

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.1997. Min Act: -0.0000

Data Index: 593439 (The Pile)

Max Activating Token Index: 181

Text #8

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.0544. Min Act: -0.0000

Data Index: 1457116 (The Pile)

Max Activating Token Index: 58

Text #9

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.0806. Min Act: -0.0000

Data Index: 811791 (The Pile)

Max Activating Token Index: 270

Text #10

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.0824. Min Act: -0.0000

Data Index: 188083 (The Pile)

Max Activating Token Index: 675

Text #11

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.1177. Min Act: -0.0000

Data Index: 304551 (The Pile)

Max Activating Token Index: 129

Text #12

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.0176. Min Act: -0.0000

Data Index: 469881 (The Pile)

Max Activating Token Index: 59

Text #13

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.0244. Min Act: -0.0000

Data Index: 1929968 (The Pile)

Max Activating Token Index: 182

Text #14

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.0451. Min Act: -0.0000

Data Index: 1768247 (The Pile)

Max Activating Token Index: 149

Text #15

Max Range: 1.3468. Min Range: -1.3468

Max Act: 0.9988. Min Act: -0.0000

Data Index: 814572 (The Pile)

Max Activating Token Index: 568

Text #16

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.0012. Min Act: -0.0000

Data Index: 885904 (The Pile)

Max Activating Token Index: 38

Text #17

Max Range: 1.3468. Min Range: -1.3468

Max Act: 0.9692. Min Act: -0.0000

Data Index: 1329238 (The Pile)

Max Activating Token Index: 265

Text #18

Max Range: 1.3468. Min Range: -1.3468

Max Act: 0.9603. Min Act: -0.0000

Data Index: 1645207 (The Pile)

Max Activating Token Index: 694

Text #19

Max Range: 1.3468. Min Range: -1.3468

Max Act: 1.0084. Min Act: -0.0000

Data Index: 1173062 (The Pile)

Max Activating Token Index: 137