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

Dataset: The Pile

Neuron 935 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3709. Min Act: -0.0000

Data Index: 879424 (The Pile)

Max Activating Token Index: 119

Text #1

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3227. Min Act: -0.0000

Data Index: 979003 (The Pile)

Max Activating Token Index: 519

Text #2

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3124. Min Act: -0.0000

Data Index: 891808 (The Pile)

Max Activating Token Index: 223

Text #3

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3102. Min Act: -0.0000

Data Index: 598030 (The Pile)

Max Activating Token Index: 56

Text #4

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3138. Min Act: -0.0000

Data Index: 306859 (The Pile)

Max Activating Token Index: 654

Text #5

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3139. Min Act: -0.0000

Data Index: 1393223 (The Pile)

Max Activating Token Index: 215

Text #6

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3030. Min Act: -0.0000

Data Index: 749686 (The Pile)

Max Activating Token Index: 329

Text #7

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3183. Min Act: -0.0000

Data Index: 541675 (The Pile)

Max Activating Token Index: 286

Text #8

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3085. Min Act: -0.0000

Data Index: 1584429 (The Pile)

Max Activating Token Index: 575

Text #9

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3129. Min Act: -0.0000

Data Index: 375498 (The Pile)

Max Activating Token Index: 595

Text #10

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3031. Min Act: -0.0000

Data Index: 1331696 (The Pile)

Max Activating Token Index: 476

Text #11

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.3042. Min Act: -0.0000

Data Index: 594476 (The Pile)

Max Activating Token Index: 777

Text #12

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1498786 (The Pile)

Max Activating Token Index: 477

Text #13

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2829. Min Act: -0.0000

Data Index: 830465 (The Pile)

Max Activating Token Index: 605

Text #14

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2897. Min Act: -0.0000

Data Index: 1419460 (The Pile)

Max Activating Token Index: 540

Text #15

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2915. Min Act: -0.0000

Data Index: 936631 (The Pile)

Max Activating Token Index: 713

Text #16

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2976. Min Act: -0.0000

Data Index: 1622874 (The Pile)

Max Activating Token Index: 200

Text #17

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2856. Min Act: -0.0000

Data Index: 967830 (The Pile)

Max Activating Token Index: 372

Text #18

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2844. Min Act: -0.0000

Data Index: 1003214 (The Pile)

Max Activating Token Index: 495

Text #19

Max Range: 0.3709. Min Range: -0.3709

Max Act: 0.2847. Min Act: -0.0000

Data Index: 1160010 (The Pile)

Max Activating Token Index: 209