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

Dataset: The Pile

Neuron 2227 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: 0.6464. Min Range: -0.6464

Max Act: 0.6464. Min Act: -0.0000

Data Index: 1762659 (The Pile)

Max Activating Token Index: 982

Text #1

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5856. Min Act: -0.0000

Data Index: 466111 (The Pile)

Max Activating Token Index: 423

Text #2

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5586. Min Act: -0.0000

Data Index: 1712785 (The Pile)

Max Activating Token Index: 653

Text #3

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5482. Min Act: -0.0000

Data Index: 555220 (The Pile)

Max Activating Token Index: 827

Text #4

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5720. Min Act: -0.0000

Data Index: 1155567 (The Pile)

Max Activating Token Index: 1015

Text #5

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5257. Min Act: -0.0000

Data Index: 586839 (The Pile)

Max Activating Token Index: 416

Text #6

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5719. Min Act: -0.0000

Data Index: 394528 (The Pile)

Max Activating Token Index: 87

Text #7

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5470. Min Act: 0.0000

Data Index: 1964651 (The Pile)

Max Activating Token Index: 620

Text #8

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4926. Min Act: -0.0000

Data Index: 1730399 (The Pile)

Max Activating Token Index: 564

Text #9

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1925708 (The Pile)

Max Activating Token Index: 250

Text #10

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4871. Min Act: -0.0000

Data Index: 442452 (The Pile)

Max Activating Token Index: 117

Text #11

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5112. Min Act: -0.0000

Data Index: 1370587 (The Pile)

Max Activating Token Index: 692

Text #12

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1535165 (The Pile)

Max Activating Token Index: 387

Text #13

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1521270 (The Pile)

Max Activating Token Index: 186

Text #14

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1001745 (The Pile)

Max Activating Token Index: 123

Text #15

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1010264 (The Pile)

Max Activating Token Index: 995

Text #16

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4973. Min Act: -0.0000

Data Index: 1694755 (The Pile)

Max Activating Token Index: 823

Text #17

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4877. Min Act: -0.0000

Data Index: 988170 (The Pile)

Max Activating Token Index: 262

Text #18

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.5018. Min Act: -0.0000

Data Index: 983151 (The Pile)

Max Activating Token Index: 904

Text #19

Max Range: 0.6464. Min Range: -0.6464

Max Act: 0.4738. Min Act: -0.0000

Data Index: 892321 (The Pile)

Max Activating Token Index: 943