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

Dataset: The Pile

Neuron 2834 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2191. Min Range: -1.2191

Max Act: 1.2191. Min Act: -0.0000

Data Index: 1103281 (The Pile)

Max Activating Token Index: 540

Text #1

Max Range: 1.2191. Min Range: -1.2191

Max Act: 1.0870. Min Act: -0.0000

Data Index: 1299392 (The Pile)

Max Activating Token Index: 306

Text #2

Max Range: 1.2191. Min Range: -1.2191

Max Act: 1.0527. Min Act: -0.0000

Data Index: 122821 (The Pile)

Max Activating Token Index: 809

Text #3

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.9416. Min Act: -0.0000

Data Index: 589121 (The Pile)

Max Activating Token Index: 539

Text #4

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.9369. Min Act: -0.0000

Data Index: 489551 (The Pile)

Max Activating Token Index: 748

Text #5

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.9347. Min Act: -0.0000

Data Index: 7442 (The Pile)

Max Activating Token Index: 161

Text #6

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.8774. Min Act: -0.0000

Data Index: 504902 (The Pile)

Max Activating Token Index: 427

Text #7

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.9241. Min Act: -0.0000

Data Index: 1061271 (The Pile)

Max Activating Token Index: 538

Text #8

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.9085. Min Act: -0.0000

Data Index: 596404 (The Pile)

Max Activating Token Index: 43

Text #9

Max Range: 1.2191. Min Range: -1.2191

Max Act: 1.0596. Min Act: -0.0000

Data Index: 1352991 (The Pile)

Max Activating Token Index: 594

Text #10

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.7921. Min Act: -0.0000

Data Index: 1642895 (The Pile)

Max Activating Token Index: 326

Text #11

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.8831. Min Act: -0.0000

Data Index: 43339 (The Pile)

Max Activating Token Index: 530

Text #12

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.8648. Min Act: -0.0000

Data Index: 1239816 (The Pile)

Max Activating Token Index: 416

Text #13

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.9067. Min Act: -0.0000

Data Index: 1758594 (The Pile)

Max Activating Token Index: 400

Text #14

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.9536. Min Act: -0.0000

Data Index: 247272 (The Pile)

Max Activating Token Index: 860

Text #15

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.8199. Min Act: -0.0000

Data Index: 1423584 (The Pile)

Max Activating Token Index: 633

Text #16

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.7657. Min Act: -0.0000

Data Index: 610562 (The Pile)

Max Activating Token Index: 263

Text #17

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.8647. Min Act: -0.0000

Data Index: 1626037 (The Pile)

Max Activating Token Index: 599

Text #18

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.9151. Min Act: -0.0000

Data Index: 837332 (The Pile)

Max Activating Token Index: 594

Text #19

Max Range: 1.2191. Min Range: -1.2191

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1442560 (The Pile)

Max Activating Token Index: 336