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

Dataset: The Pile

Neuron 3568 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: 1.9983. Min Range: -1.9983

Max Act: 1.9983. Min Act: -0.0000

Data Index: 880133 (The Pile)

Max Activating Token Index: 664

Text #1

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.7441. Min Act: -0.0000

Data Index: 157114 (The Pile)

Max Activating Token Index: 20

Text #2

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.6824. Min Act: -0.0000

Data Index: 1951472 (The Pile)

Max Activating Token Index: 289

Text #3

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.6020. Min Act: -0.0000

Data Index: 1166105 (The Pile)

Max Activating Token Index: 159

Text #4

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.5041. Min Act: -0.0000

Data Index: 1184978 (The Pile)

Max Activating Token Index: 619

Text #5

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.4298. Min Act: -0.0000

Data Index: 690492 (The Pile)

Max Activating Token Index: 956

Text #6

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.5196. Min Act: -0.0000

Data Index: 1165876 (The Pile)

Max Activating Token Index: 828

Text #7

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.6559. Min Act: -0.0000

Data Index: 1953014 (The Pile)

Max Activating Token Index: 85

Text #8

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.5148. Min Act: -0.0000

Data Index: 1384036 (The Pile)

Max Activating Token Index: 965

Text #9

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.5625. Min Act: -0.0000

Data Index: 733301 (The Pile)

Max Activating Token Index: 497

Text #10

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.5776. Min Act: -0.0000

Data Index: 514196 (The Pile)

Max Activating Token Index: 284

Text #11

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.5100. Min Act: -0.0000

Data Index: 980476 (The Pile)

Max Activating Token Index: 383

Text #12

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.4327. Min Act: -0.0000

Data Index: 216849 (The Pile)

Max Activating Token Index: 108

Text #13

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.4250. Min Act: -0.0000

Data Index: 1002051 (The Pile)

Max Activating Token Index: 287

Text #14

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.4710. Min Act: -0.0000

Data Index: 1556498 (The Pile)

Max Activating Token Index: 795

Text #15

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.4040. Min Act: -0.0000

Data Index: 1192798 (The Pile)

Max Activating Token Index: 422

Text #16

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.4437. Min Act: -0.0000

Data Index: 1388055 (The Pile)

Max Activating Token Index: 671

Text #17

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.4312. Min Act: -0.0000

Data Index: 98057 (The Pile)

Max Activating Token Index: 557

Text #18

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.3916. Min Act: -0.0000

Data Index: 663914 (The Pile)

Max Activating Token Index: 214

Text #19

Max Range: 1.9983. Min Range: -1.9983

Max Act: 1.4711. Min Act: -0.0000

Data Index: 917396 (The Pile)

Max Activating Token Index: 859