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

Dataset: The Pile

Neuron 170 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: 0.4128. Min Range: -0.4128

Max Act: 0.4128. Min Act: -0.0000

Data Index: 163642 (The Pile)

Max Activating Token Index: 75

Text #1

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3730. Min Act: -0.0000

Data Index: 678763 (The Pile)

Max Activating Token Index: 76

Text #2

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3427. Min Act: -0.0000

Data Index: 1840149 (The Pile)

Max Activating Token Index: 754

Text #3

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3594. Min Act: -0.0000

Data Index: 1785534 (The Pile)

Max Activating Token Index: 738

Text #4

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1444577 (The Pile)

Max Activating Token Index: 337

Text #5

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3504. Min Act: -0.0000

Data Index: 1665422 (The Pile)

Max Activating Token Index: 816

Text #6

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3386. Min Act: -0.0000

Data Index: 1905629 (The Pile)

Max Activating Token Index: 67

Text #7

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3257. Min Act: -0.0000

Data Index: 178538 (The Pile)

Max Activating Token Index: 118

Text #8

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3261. Min Act: -0.0000

Data Index: 1710422 (The Pile)

Max Activating Token Index: 170

Text #9

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3278. Min Act: -0.0000

Data Index: 1661535 (The Pile)

Max Activating Token Index: 81

Text #10

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.2982. Min Act: -0.0000

Data Index: 692069 (The Pile)

Max Activating Token Index: 510

Text #11

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3300. Min Act: -0.0000

Data Index: 1612150 (The Pile)

Max Activating Token Index: 200

Text #12

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1639800 (The Pile)

Max Activating Token Index: 222

Text #13

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.2827. Min Act: -0.0000

Data Index: 1041289 (The Pile)

Max Activating Token Index: 71

Text #14

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3064. Min Act: -0.0000

Data Index: 1797451 (The Pile)

Max Activating Token Index: 145

Text #15

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1236346 (The Pile)

Max Activating Token Index: 560

Text #16

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.2943. Min Act: -0.0000

Data Index: 730853 (The Pile)

Max Activating Token Index: 176

Text #17

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.2829. Min Act: -0.0000

Data Index: 287999 (The Pile)

Max Activating Token Index: 104

Text #18

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.3099. Min Act: -0.0000

Data Index: 723145 (The Pile)

Max Activating Token Index: 64

Text #19

Max Range: 0.4128. Min Range: -0.4128

Max Act: 0.2890. Min Act: -0.0000

Data Index: 329420 (The Pile)

Max Activating Token Index: 315