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

Dataset: The Pile

Neuron 4497 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: 1.4667. Min Range: -1.4667

Max Act: 1.4667. Min Act: -0.0000

Data Index: 682184 (The Pile)

Max Activating Token Index: 220

Text #1

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.3886. Min Act: -0.0000

Data Index: 1785515 (The Pile)

Max Activating Token Index: 196

Text #2

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.4619. Min Act: -0.0000

Data Index: 256859 (The Pile)

Max Activating Token Index: 321

Text #3

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.4588. Min Act: -0.0000

Data Index: 1660065 (The Pile)

Max Activating Token Index: 237

Text #4

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.3666. Min Act: -0.0000

Data Index: 1102721 (The Pile)

Max Activating Token Index: 311

Text #5

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.4225. Min Act: -0.0000

Data Index: 481881 (The Pile)

Max Activating Token Index: 261

Text #6

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.3129. Min Act: -0.0000

Data Index: 1949911 (The Pile)

Max Activating Token Index: 382

Text #7

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.4619. Min Act: -0.0000

Data Index: 1430339 (The Pile)

Max Activating Token Index: 141

Text #8

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.4635. Min Act: -0.0000

Data Index: 1653412 (The Pile)

Max Activating Token Index: 213

Text #9

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.3677. Min Act: -0.0000

Data Index: 1863697 (The Pile)

Max Activating Token Index: 474

Text #10

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.3618. Min Act: -0.0000

Data Index: 1552240 (The Pile)

Max Activating Token Index: 41

Text #11

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.2895. Min Act: -0.0000

Data Index: 1903190 (The Pile)

Max Activating Token Index: 939

Text #12

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.3571. Min Act: -0.0000

Data Index: 1388862 (The Pile)

Max Activating Token Index: 142

Text #13

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.2807. Min Act: -0.0000

Data Index: 1645407 (The Pile)

Max Activating Token Index: 775

Text #14

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.3081. Min Act: -0.0000

Data Index: 1241497 (The Pile)

Max Activating Token Index: 557

Text #15

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.2351. Min Act: -0.0000

Data Index: 1344140 (The Pile)

Max Activating Token Index: 740

Text #16

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.2332. Min Act: -0.0000

Data Index: 1804999 (The Pile)

Max Activating Token Index: 433

Text #17

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.3012. Min Act: -0.0000

Data Index: 1262920 (The Pile)

Max Activating Token Index: 761

Text #18

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.2910. Min Act: -0.0000

Data Index: 1536135 (The Pile)

Max Activating Token Index: 824

Text #19

Max Range: 1.4667. Min Range: -1.4667

Max Act: 1.2903. Min Act: -0.0000

Data Index: 1544910 (The Pile)

Max Activating Token Index: 1008