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

Dataset: The Pile

Neuron 1950 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.6261. Min Act: -0.0000

Data Index: 291995 (The Pile)

Max Activating Token Index: 161

Text #1

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.5216. Min Act: -0.0000

Data Index: 534964 (The Pile)

Max Activating Token Index: 691

Text #2

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.3829. Min Act: -0.0000

Data Index: 72950 (The Pile)

Max Activating Token Index: 134

Text #3

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.3393. Min Act: -0.0000

Data Index: 1127691 (The Pile)

Max Activating Token Index: 926

Text #4

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.1068. Min Act: -0.0000

Data Index: 1337564 (The Pile)

Max Activating Token Index: 887

Text #5

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.3237. Min Act: -0.0000

Data Index: 83168 (The Pile)

Max Activating Token Index: 977

Text #6

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.1855. Min Act: -0.0000

Data Index: 1067409 (The Pile)

Max Activating Token Index: 541

Text #7

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.1787. Min Act: -0.0000

Data Index: 1465159 (The Pile)

Max Activating Token Index: 35

Text #8

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.1183. Min Act: -0.0000

Data Index: 417196 (The Pile)

Max Activating Token Index: 204

Text #9

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.2494. Min Act: -0.0000

Data Index: 1165169 (The Pile)

Max Activating Token Index: 115

Text #10

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.2372. Min Act: -0.0000

Data Index: 1062591 (The Pile)

Max Activating Token Index: 13

Text #11

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.1612. Min Act: -0.0000

Data Index: 699308 (The Pile)

Max Activating Token Index: 422

Text #12

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.1550. Min Act: -0.0000

Data Index: 220925 (The Pile)

Max Activating Token Index: 888

Text #13

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.2133. Min Act: -0.0000

Data Index: 108374 (The Pile)

Max Activating Token Index: 501

Text #14

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.1399. Min Act: -0.0000

Data Index: 1020242 (The Pile)

Max Activating Token Index: 660

Text #15

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.1341. Min Act: -0.0000

Data Index: 1216003 (The Pile)

Max Activating Token Index: 390

Text #16

Max Range: 1.6261. Min Range: -1.6261

Max Act: 0.9902. Min Act: -0.0000

Data Index: 1713714 (The Pile)

Max Activating Token Index: 119

Text #17

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.1241. Min Act: -0.0000

Data Index: 1563284 (The Pile)

Max Activating Token Index: 990

Text #18

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.1182. Min Act: -0.0000

Data Index: 1626605 (The Pile)

Max Activating Token Index: 29

Text #19

Max Range: 1.6261. Min Range: -1.6261

Max Act: 1.0486. Min Act: -0.0000

Data Index: 765002 (The Pile)

Max Activating Token Index: 777