Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 354 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0195. Min Range: -1.0195

Max Act: 1.0195. Min Act: -0.0000

Data Index: 1071761 (The Pile)

Max Activating Token Index: 443

Text #1

Max Range: 1.0195. Min Range: -1.0195

Max Act: 1.0071. Min Act: -0.0000

Data Index: 1678201 (The Pile)

Max Activating Token Index: 340

Text #2

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.9601. Min Act: -0.0000

Data Index: 19685 (The Pile)

Max Activating Token Index: 277

Text #3

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8675. Min Act: -0.0000

Data Index: 630250 (The Pile)

Max Activating Token Index: 840

Text #4

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8289. Min Act: -0.0000

Data Index: 1773999 (The Pile)

Max Activating Token Index: 75

Text #5

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8045. Min Act: -0.0000

Data Index: 135567 (The Pile)

Max Activating Token Index: 767

Text #6

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7899. Min Act: -0.0000

Data Index: 1229837 (The Pile)

Max Activating Token Index: 891

Text #7

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7481. Min Act: -0.0000

Data Index: 567212 (The Pile)

Max Activating Token Index: 323

Text #8

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7507. Min Act: -0.0000

Data Index: 962021 (The Pile)

Max Activating Token Index: 42

Text #9

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7615. Min Act: -0.0000

Data Index: 151216 (The Pile)

Max Activating Token Index: 1019

Text #10

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1444517 (The Pile)

Max Activating Token Index: 645

Text #11

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.6701. Min Act: -0.0000

Data Index: 688106 (The Pile)

Max Activating Token Index: 1022

Text #12

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.6704. Min Act: -0.0000

Data Index: 1361666 (The Pile)

Max Activating Token Index: 254

Text #13

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1113246 (The Pile)

Max Activating Token Index: 918

Text #14

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.6562. Min Act: -0.0000

Data Index: 82047 (The Pile)

Max Activating Token Index: 550

Text #15

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.6384. Min Act: -0.0000

Data Index: 698362 (The Pile)

Max Activating Token Index: 904

Text #16

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.6818. Min Act: -0.0000

Data Index: 373175 (The Pile)

Max Activating Token Index: 858

Text #17

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.6443. Min Act: -0.0000

Data Index: 1504064 (The Pile)

Max Activating Token Index: 13

Text #18

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.6588. Min Act: -0.0000

Data Index: 394272 (The Pile)

Max Activating Token Index: 450

Text #19

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.5848. Min Act: -0.0000

Data Index: 1318442 (The Pile)

Max Activating Token Index: 404