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

Dataset: The Pile

Neuron 4450 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: 0.9666. Min Range: -0.9666

Max Act: 0.9666. Min Act: -0.0000

Data Index: 517058 (The Pile)

Max Activating Token Index: 933

Text #1

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.9129. Min Act: -0.0000

Data Index: 103379 (The Pile)

Max Activating Token Index: 3

Text #2

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.9111. Min Act: -0.0000

Data Index: 1218909 (The Pile)

Max Activating Token Index: 924

Text #3

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.9013. Min Act: -0.0000

Data Index: 108781 (The Pile)

Max Activating Token Index: 76

Text #4

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.8890. Min Act: -0.0000

Data Index: 1517906 (The Pile)

Max Activating Token Index: 80

Text #5

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.9203. Min Act: -0.0000

Data Index: 1698346 (The Pile)

Max Activating Token Index: 264

Text #6

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.9192. Min Act: -0.0000

Data Index: 1834593 (The Pile)

Max Activating Token Index: 71

Text #7

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.8766. Min Act: -0.0000

Data Index: 1951094 (The Pile)

Max Activating Token Index: 363

Text #8

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.8682. Min Act: -0.0000

Data Index: 98603 (The Pile)

Max Activating Token Index: 459

Text #9

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.8678. Min Act: -0.0000

Data Index: 1876058 (The Pile)

Max Activating Token Index: 108

Text #10

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.9448. Min Act: -0.0000

Data Index: 236929 (The Pile)

Max Activating Token Index: 323

Text #11

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.9068. Min Act: -0.0000

Data Index: 202198 (The Pile)

Max Activating Token Index: 836

Text #12

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.8543. Min Act: -0.0000

Data Index: 582192 (The Pile)

Max Activating Token Index: 919

Text #13

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.9136. Min Act: -0.0000

Data Index: 1321132 (The Pile)

Max Activating Token Index: 54

Text #14

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.9074. Min Act: -0.0000

Data Index: 1350789 (The Pile)

Max Activating Token Index: 267

Text #15

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.8403. Min Act: -0.0000

Data Index: 1191926 (The Pile)

Max Activating Token Index: 417

Text #16

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.8464. Min Act: -0.0000

Data Index: 361664 (The Pile)

Max Activating Token Index: 396

Text #17

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.8275. Min Act: -0.0000

Data Index: 315778 (The Pile)

Max Activating Token Index: 989

Text #18

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.8252. Min Act: -0.0000

Data Index: 79573 (The Pile)

Max Activating Token Index: 1018

Text #19

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.8226. Min Act: -0.0000

Data Index: 1200167 (The Pile)

Max Activating Token Index: 263