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

Dataset: The Pile

Neuron 3403 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: 0.5533. Min Range: -0.5533

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1464076 (The Pile)

Max Activating Token Index: 712

Text #1

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4035. Min Act: -0.0000

Data Index: 714212 (The Pile)

Max Activating Token Index: 504

Text #2

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3887. Min Act: -0.0000

Data Index: 1317283 (The Pile)

Max Activating Token Index: 281

Text #3

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3896. Min Act: -0.0000

Data Index: 1425966 (The Pile)

Max Activating Token Index: 96

Text #4

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1218912 (The Pile)

Max Activating Token Index: 552

Text #5

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3708. Min Act: -0.0000

Data Index: 1008801 (The Pile)

Max Activating Token Index: 176

Text #6

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3866. Min Act: -0.0000

Data Index: 925876 (The Pile)

Max Activating Token Index: 896

Text #7

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3502. Min Act: -0.0001

Data Index: 1630618 (The Pile)

Max Activating Token Index: 387

Text #8

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3313. Min Act: 0.0000

Data Index: 738304 (The Pile)

Max Activating Token Index: 535

Text #9

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3721. Min Act: -0.0000

Data Index: 272094 (The Pile)

Max Activating Token Index: 81

Text #10

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3774. Min Act: -0.0000

Data Index: 1391283 (The Pile)

Max Activating Token Index: 894

Text #11

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3485. Min Act: -0.0000

Data Index: 892520 (The Pile)

Max Activating Token Index: 291

Text #12

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.2938. Min Act: -0.0000

Data Index: 764491 (The Pile)

Max Activating Token Index: 540

Text #13

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3500. Min Act: -0.0000

Data Index: 903277 (The Pile)

Max Activating Token Index: 190

Text #14

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3178. Min Act: -0.0000

Data Index: 1047076 (The Pile)

Max Activating Token Index: 139

Text #15

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1316257 (The Pile)

Max Activating Token Index: 448

Text #16

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3411. Min Act: -0.0000

Data Index: 1576957 (The Pile)

Max Activating Token Index: 132

Text #17

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3366. Min Act: -0.0000

Data Index: 549902 (The Pile)

Max Activating Token Index: 534

Text #18

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3317. Min Act: -0.0000

Data Index: 1145414 (The Pile)

Max Activating Token Index: 850

Text #19

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3308. Min Act: -0.0000

Data Index: 461813 (The Pile)

Max Activating Token Index: 759