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

Dataset: The Pile

Neuron 631 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: 0.8409. Min Range: -0.8409

Max Act: 0.8409. Min Act: -0.0000

Data Index: 522312 (The Pile)

Max Activating Token Index: 71

Text #1

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.6520. Min Act: -0.0000

Data Index: 86289 (The Pile)

Max Activating Token Index: 242

Text #2

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.7243. Min Act: -0.0000

Data Index: 808209 (The Pile)

Max Activating Token Index: 669

Text #3

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.6573. Min Act: -0.0000

Data Index: 695200 (The Pile)

Max Activating Token Index: 487

Text #4

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5822. Min Act: -0.0000

Data Index: 841006 (The Pile)

Max Activating Token Index: 998

Text #5

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1064194 (The Pile)

Max Activating Token Index: 843

Text #6

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5445. Min Act: -0.0000

Data Index: 1649993 (The Pile)

Max Activating Token Index: 493

Text #7

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.6297. Min Act: -0.0000

Data Index: 735964 (The Pile)

Max Activating Token Index: 633

Text #8

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5411. Min Act: -0.0000

Data Index: 811898 (The Pile)

Max Activating Token Index: 208

Text #9

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.6071. Min Act: -0.0000

Data Index: 1878468 (The Pile)

Max Activating Token Index: 185

Text #10

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5683. Min Act: -0.0000

Data Index: 961868 (The Pile)

Max Activating Token Index: 820

Text #11

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1749135 (The Pile)

Max Activating Token Index: 350

Text #12

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5661. Min Act: -0.0000

Data Index: 720266 (The Pile)

Max Activating Token Index: 120

Text #13

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5172. Min Act: -0.0000

Data Index: 12042 (The Pile)

Max Activating Token Index: 737

Text #14

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1219204 (The Pile)

Max Activating Token Index: 839

Text #15

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5187. Min Act: -0.0000

Data Index: 1654797 (The Pile)

Max Activating Token Index: 675

Text #16

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5293. Min Act: -0.0000

Data Index: 1277076 (The Pile)

Max Activating Token Index: 9

Text #17

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1201687 (The Pile)

Max Activating Token Index: 981

Text #18

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.4383. Min Act: -0.0000

Data Index: 116039 (The Pile)

Max Activating Token Index: 755

Text #19

Max Range: 0.8409. Min Range: -0.8409

Max Act: 0.5123. Min Act: -0.0000

Data Index: 1046743 (The Pile)

Max Activating Token Index: 214