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

Dataset: The Pile

Neuron 900 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: 0.6757. Min Range: -0.6757

Max Act: 0.6757. Min Act: -0.0000

Data Index: 1454322 (The Pile)

Max Activating Token Index: 423

Text #1

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.6416. Min Act: -0.0000

Data Index: 30410 (The Pile)

Max Activating Token Index: 959

Text #2

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.6074. Min Act: -0.0000

Data Index: 914435 (The Pile)

Max Activating Token Index: 66

Text #3

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4987. Min Act: -0.0000

Data Index: 734112 (The Pile)

Max Activating Token Index: 433

Text #4

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4974. Min Act: -0.0000

Data Index: 1981028 (The Pile)

Max Activating Token Index: 103

Text #5

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.5571. Min Act: -0.0000

Data Index: 178417 (The Pile)

Max Activating Token Index: 876

Text #6

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4983. Min Act: -0.0000

Data Index: 1352236 (The Pile)

Max Activating Token Index: 920

Text #7

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4169. Min Act: -0.0000

Data Index: 1916491 (The Pile)

Max Activating Token Index: 169

Text #8

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1845788 (The Pile)

Max Activating Token Index: 116

Text #9

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4644. Min Act: -0.0000

Data Index: 849826 (The Pile)

Max Activating Token Index: 127

Text #10

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1599528 (The Pile)

Max Activating Token Index: 23

Text #11

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4132. Min Act: -0.0000

Data Index: 210632 (The Pile)

Max Activating Token Index: 817

Text #12

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4172. Min Act: -0.0000

Data Index: 236643 (The Pile)

Max Activating Token Index: 257

Text #13

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4626. Min Act: -0.0000

Data Index: 43100 (The Pile)

Max Activating Token Index: 9

Text #14

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4282. Min Act: -0.0000

Data Index: 117936 (The Pile)

Max Activating Token Index: 40

Text #15

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4339. Min Act: -0.0000

Data Index: 1933832 (The Pile)

Max Activating Token Index: 285

Text #16

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1117065 (The Pile)

Max Activating Token Index: 716

Text #17

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1200510 (The Pile)

Max Activating Token Index: 957

Text #18

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4181. Min Act: -0.0000

Data Index: 623232 (The Pile)

Max Activating Token Index: 265

Text #19

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4285. Min Act: -0.0000

Data Index: 915190 (The Pile)

Max Activating Token Index: 166