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

Dataset: The Pile

Neuron 1693 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.8431. Min Act: -0.0000

Data Index: 1877197 (The Pile)

Max Activating Token Index: 929

Text #1

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.7088. Min Act: -0.0000

Data Index: 774517 (The Pile)

Max Activating Token Index: 224

Text #2

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.6787. Min Act: -0.0000

Data Index: 1472141 (The Pile)

Max Activating Token Index: 96

Text #3

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.6738. Min Act: -0.0000

Data Index: 1941621 (The Pile)

Max Activating Token Index: 39

Text #4

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.6330. Min Act: -0.0000

Data Index: 890 (The Pile)

Max Activating Token Index: 328

Text #5

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1100061 (The Pile)

Max Activating Token Index: 1010

Text #6

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.6143. Min Act: -0.0000

Data Index: 1660304 (The Pile)

Max Activating Token Index: 233

Text #7

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.5761. Min Act: -0.0000

Data Index: 1012230 (The Pile)

Max Activating Token Index: 278

Text #8

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.5614. Min Act: -0.0000

Data Index: 1418424 (The Pile)

Max Activating Token Index: 101

Text #9

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.5780. Min Act: -0.0000

Data Index: 1133583 (The Pile)

Max Activating Token Index: 374

Text #10

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.5446. Min Act: -0.0000

Data Index: 492010 (The Pile)

Max Activating Token Index: 920

Text #11

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1154180 (The Pile)

Max Activating Token Index: 1008

Text #12

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.5323. Min Act: -0.0000

Data Index: 170595 (The Pile)

Max Activating Token Index: 500

Text #13

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.5198. Min Act: -0.0000

Data Index: 986433 (The Pile)

Max Activating Token Index: 28

Text #14

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.5075. Min Act: -0.0000

Data Index: 507223 (The Pile)

Max Activating Token Index: 977

Text #15

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.5085. Min Act: -0.0000

Data Index: 1876281 (The Pile)

Max Activating Token Index: 396

Text #16

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.5482. Min Act: -0.0000

Data Index: 126415 (The Pile)

Max Activating Token Index: 133

Text #17

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1040241 (The Pile)

Max Activating Token Index: 177

Text #18

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.5068. Min Act: -0.0000

Data Index: 1112222 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1564077 (The Pile)

Max Activating Token Index: 782