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

Dataset: The Pile

Neuron 5028 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: 1.2441. Min Range: -1.2441

Max Act: 1.1946. Min Act: -0.0000

Data Index: 1584576 (The Pile)

Max Activating Token Index: 615

Text #1

Max Range: 1.2441. Min Range: -1.2441

Max Act: 1.2441. Min Act: -0.0000

Data Index: 128543 (The Pile)

Max Activating Token Index: 635

Text #2

Max Range: 1.2441. Min Range: -1.2441

Max Act: 1.1316. Min Act: -0.0000

Data Index: 123863 (The Pile)

Max Activating Token Index: 971

Text #3

Max Range: 1.2441. Min Range: -1.2441

Max Act: 1.1674. Min Act: -0.0000

Data Index: 430758 (The Pile)

Max Activating Token Index: 779

Text #4

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.9896. Min Act: -0.0000

Data Index: 1585761 (The Pile)

Max Activating Token Index: 945

Text #5

Max Range: 1.2441. Min Range: -1.2441

Max Act: 1.0962. Min Act: -0.0000

Data Index: 1961260 (The Pile)

Max Activating Token Index: 116

Text #6

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.9994. Min Act: -0.0000

Data Index: 1589501 (The Pile)

Max Activating Token Index: 175

Text #7

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.9953. Min Act: -0.0000

Data Index: 460183 (The Pile)

Max Activating Token Index: 268

Text #8

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.9794. Min Act: -0.0000

Data Index: 619151 (The Pile)

Max Activating Token Index: 813

Text #9

Max Range: 1.2441. Min Range: -1.2441

Max Act: 1.0234. Min Act: -0.0000

Data Index: 1223398 (The Pile)

Max Activating Token Index: 224

Text #10

Max Range: 1.2441. Min Range: -1.2441

Max Act: 1.1415. Min Act: -0.0000

Data Index: 1207429 (The Pile)

Max Activating Token Index: 1010

Text #11

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.9537. Min Act: -0.0000

Data Index: 1650077 (The Pile)

Max Activating Token Index: 371

Text #12

Max Range: 1.2441. Min Range: -1.2441

Max Act: 1.0125. Min Act: -0.0000

Data Index: 290381 (The Pile)

Max Activating Token Index: 371

Text #13

Max Range: 1.2441. Min Range: -1.2441

Max Act: 1.0170. Min Act: -0.0000

Data Index: 1519194 (The Pile)

Max Activating Token Index: 283

Text #14

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.9898. Min Act: -0.0000

Data Index: 814647 (The Pile)

Max Activating Token Index: 111

Text #15

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.9958. Min Act: 0.0000

Data Index: 223569 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 1.2441. Min Range: -1.2441

Max Act: 1.0416. Min Act: -0.0000

Data Index: 864471 (The Pile)

Max Activating Token Index: 980

Text #17

Max Range: 1.2441. Min Range: -1.2441

Max Act: 1.0169. Min Act: -0.0000

Data Index: 1016615 (The Pile)

Max Activating Token Index: 753

Text #18

Max Range: 1.2441. Min Range: -1.2441

Max Act: 1.0209. Min Act: -0.0000

Data Index: 1582402 (The Pile)

Max Activating Token Index: 888

Text #19

Max Range: 1.2441. Min Range: -1.2441

Max Act: 0.9512. Min Act: -0.0000

Data Index: 1788213 (The Pile)

Max Activating Token Index: 580