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

Dataset: The Pile

Neuron 1956 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2048. Min Range: -2.2048

Max Act: 2.2048. Min Act: -0.0000

Data Index: 1306692 (The Pile)

Max Activating Token Index: 200

Text #1

Max Range: 2.2048. Min Range: -2.2048

Max Act: 2.1933. Min Act: -0.0000

Data Index: 92757 (The Pile)

Max Activating Token Index: 18

Text #2

Max Range: 2.2048. Min Range: -2.2048

Max Act: 2.1548. Min Act: -0.0000

Data Index: 852903 (The Pile)

Max Activating Token Index: 940

Text #3

Max Range: 2.2048. Min Range: -2.2048

Max Act: 2.0501. Min Act: -0.0000

Data Index: 1001063 (The Pile)

Max Activating Token Index: 940

Text #4

Max Range: 2.2048. Min Range: -2.2048

Max Act: 1.9221. Min Act: -0.0000

Data Index: 635579 (The Pile)

Max Activating Token Index: 437

Text #5

Max Range: 2.2048. Min Range: -2.2048

Max Act: 1.9197. Min Act: -0.0000

Data Index: 1513452 (The Pile)

Max Activating Token Index: 764

Text #6

Max Range: 2.2048. Min Range: -2.2048

Max Act: 1.8990. Min Act: -0.0000

Data Index: 310101 (The Pile)

Max Activating Token Index: 89

Text #7

Max Range: 2.2048. Min Range: -2.2048

Max Act: 1.8925. Min Act: -0.0000

Data Index: 478216 (The Pile)

Max Activating Token Index: 780

Text #8

Max Range: 2.2048. Min Range: -2.2048

Max Act: 1.7193. Min Act: -0.0000

Data Index: 1709578 (The Pile)

Max Activating Token Index: 204

Text #9

Max Range: 2.2048. Min Range: -2.2048

Max Act: 1.7085. Min Act: -0.0000

Data Index: 1252632 (The Pile)

Max Activating Token Index: 410

Text #10

Max Range: 2.2048. Min Range: -2.2048

Max Act: 1.8811. Min Act: -0.0000

Data Index: 260098 (The Pile)

Max Activating Token Index: 437

Text #11

Max Range: 2.2048. Min Range: -2.2048

Max Act: 1.7401. Min Act: -0.0000

Data Index: 281375 (The Pile)

Max Activating Token Index: 907

Text #12

Max Range: 2.2048. Min Range: -2.2048

Max Act: 1.6690. Min Act: -0.0000

Data Index: 1788478 (The Pile)

Max Activating Token Index: 536

Text #13

Max Range: 2.2048. Min Range: -2.2048

Max Act: 1.7576. Min Act: -0.0000

Data Index: 408714 (The Pile)

Max Activating Token Index: 395

Text #14

Max Range: 2.2048. Min Range: -2.2048

Max Act: 1.7521. Min Act: -0.0000

Data Index: 762529 (The Pile)

Max Activating Token Index: 320

Text #15

Max Range: 2.2048. Min Range: -2.2048

Max Act: 1.6380. Min Act: -0.0000

Data Index: 1925853 (The Pile)

Max Activating Token Index: 520

Text #16

Max Range: 2.2048. Min Range: -2.2048

Max Act: 1.7452. Min Act: -0.0000

Data Index: 816610 (The Pile)

Max Activating Token Index: 198

Text #17

Max Range: 2.2048. Min Range: -2.2048

Max Act: 1.6404. Min Act: -0.0000

Data Index: 1142894 (The Pile)

Max Activating Token Index: 436

Text #18

Max Range: 2.2048. Min Range: -2.2048

Max Act: 1.7258. Min Act: -0.0000

Data Index: 1230707 (The Pile)

Max Activating Token Index: 50

Text #19

Max Range: 2.2048. Min Range: -2.2048

Max Act: 1.6378. Min Act: -0.0000

Data Index: 989537 (The Pile)

Max Activating Token Index: 137