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

Dataset: The Pile

Neuron 1356 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: 0.9666. Min Range: -0.9666

Max Act: 0.9666. Min Act: -0.0000

Data Index: 1718357 (The Pile)

Max Activating Token Index: 135

Text #1

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.9511. Min Act: -0.0000

Data Index: 712748 (The Pile)

Max Activating Token Index: 394

Text #2

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.7250. Min Act: -0.0000

Data Index: 1026618 (The Pile)

Max Activating Token Index: 774

Text #3

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.8764. Min Act: -0.0000

Data Index: 690654 (The Pile)

Max Activating Token Index: 987

Text #4

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.7792. Min Act: -0.0000

Data Index: 1013979 (The Pile)

Max Activating Token Index: 227

Text #5

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.8275. Min Act: -0.0000

Data Index: 1566311 (The Pile)

Max Activating Token Index: 165

Text #6

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.7678. Min Act: -0.0000

Data Index: 880905 (The Pile)

Max Activating Token Index: 766

Text #7

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.7852. Min Act: -0.0000

Data Index: 1038275 (The Pile)

Max Activating Token Index: 112

Text #8

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.7583. Min Act: -0.0000

Data Index: 357059 (The Pile)

Max Activating Token Index: 481

Text #9

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.7764. Min Act: -0.0000

Data Index: 554901 (The Pile)

Max Activating Token Index: 312

Text #10

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.7733. Min Act: -0.0000

Data Index: 61932 (The Pile)

Max Activating Token Index: 1018

Text #11

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.7236. Min Act: -0.0000

Data Index: 141234 (The Pile)

Max Activating Token Index: 714

Text #12

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.7623. Min Act: -0.0000

Data Index: 236236 (The Pile)

Max Activating Token Index: 98

Text #13

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.7267. Min Act: -0.0000

Data Index: 873253 (The Pile)

Max Activating Token Index: 278

Text #14

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.7773. Min Act: -0.0000

Data Index: 305384 (The Pile)

Max Activating Token Index: 405

Text #15

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1071054 (The Pile)

Max Activating Token Index: 47

Text #16

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.7301. Min Act: -0.0000

Data Index: 206415 (The Pile)

Max Activating Token Index: 387

Text #17

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.7388. Min Act: -0.0000

Data Index: 694294 (The Pile)

Max Activating Token Index: 911

Text #18

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.7392. Min Act: -0.0000

Data Index: 189157 (The Pile)

Max Activating Token Index: 604

Text #19

Max Range: 0.9666. Min Range: -0.9666

Max Act: 0.7263. Min Act: -0.0000

Data Index: 441199 (The Pile)

Max Activating Token Index: 1003