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

Dataset: The Pile

Neuron 1891 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.9927. Min Act: -0.0000

Data Index: 1504223 (The Pile)

Max Activating Token Index: 837

Text #1

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.9264. Min Act: -0.0000

Data Index: 1847103 (The Pile)

Max Activating Token Index: 76

Text #2

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.9766. Min Act: -0.0000

Data Index: 693827 (The Pile)

Max Activating Token Index: 1020

Text #3

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.8269. Min Act: -0.0000

Data Index: 1494523 (The Pile)

Max Activating Token Index: 206

Text #4

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.9585. Min Act: -0.0000

Data Index: 474076 (The Pile)

Max Activating Token Index: 456

Text #5

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7527. Min Act: -0.0000

Data Index: 1014963 (The Pile)

Max Activating Token Index: 695

Text #6

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.8478. Min Act: -0.0000

Data Index: 855410 (The Pile)

Max Activating Token Index: 153

Text #7

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1547311 (The Pile)

Max Activating Token Index: 529

Text #8

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.8168. Min Act: -0.0000

Data Index: 748113 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7288. Min Act: -0.0000

Data Index: 664627 (The Pile)

Max Activating Token Index: 640

Text #10

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7486. Min Act: -0.0000

Data Index: 713818 (The Pile)

Max Activating Token Index: 158

Text #11

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7304. Min Act: -0.0000

Data Index: 1278824 (The Pile)

Max Activating Token Index: 633

Text #12

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7140. Min Act: -0.0000

Data Index: 1989760 (The Pile)

Max Activating Token Index: 972

Text #13

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7193. Min Act: -0.0000

Data Index: 118287 (The Pile)

Max Activating Token Index: 491

Text #14

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6559. Min Act: -0.0000

Data Index: 789567 (The Pile)

Max Activating Token Index: 760

Text #15

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6935. Min Act: -0.0000

Data Index: 208889 (The Pile)

Max Activating Token Index: 392

Text #16

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7191. Min Act: -0.0000

Data Index: 1247241 (The Pile)

Max Activating Token Index: 1007

Text #17

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6860. Min Act: -0.0000

Data Index: 1256216 (The Pile)

Max Activating Token Index: 549

Text #18

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7101. Min Act: -0.0000

Data Index: 1110175 (The Pile)

Max Activating Token Index: 456

Text #19

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7091. Min Act: -0.0000

Data Index: 1880546 (The Pile)

Max Activating Token Index: 234