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

Dataset: The Pile

Neuron 747 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: 0.6513. Min Range: -0.6513

Max Act: 0.6513. Min Act: -0.0000

Data Index: 640864 (The Pile)

Max Activating Token Index: 454

Text #1

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5658. Min Act: -0.0000

Data Index: 505063 (The Pile)

Max Activating Token Index: 533

Text #2

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1667248 (The Pile)

Max Activating Token Index: 1001

Text #3

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1368652 (The Pile)

Max Activating Token Index: 775

Text #4

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1275062 (The Pile)

Max Activating Token Index: 1012

Text #5

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1194315 (The Pile)

Max Activating Token Index: 806

Text #6

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5687. Min Act: -0.0000

Data Index: 20077 (The Pile)

Max Activating Token Index: 405

Text #7

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5648. Min Act: -0.0000

Data Index: 1113001 (The Pile)

Max Activating Token Index: 563

Text #8

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5360. Min Act: -0.0000

Data Index: 1952043 (The Pile)

Max Activating Token Index: 947

Text #9

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5244. Min Act: -0.0000

Data Index: 712012 (The Pile)

Max Activating Token Index: 372

Text #10

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5430. Min Act: -0.0000

Data Index: 165306 (The Pile)

Max Activating Token Index: 839

Text #11

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1406378 (The Pile)

Max Activating Token Index: 845

Text #12

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1703510 (The Pile)

Max Activating Token Index: 939

Text #13

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1643934 (The Pile)

Max Activating Token Index: 633

Text #14

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5067. Min Act: -0.0000

Data Index: 760327 (The Pile)

Max Activating Token Index: 233

Text #15

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1575101 (The Pile)

Max Activating Token Index: 542

Text #16

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4717. Min Act: -0.0000

Data Index: 809815 (The Pile)

Max Activating Token Index: 526

Text #17

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4848. Min Act: -0.0000

Data Index: 1379986 (The Pile)

Max Activating Token Index: 740

Text #18

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5079. Min Act: -0.0000

Data Index: 724191 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4939. Min Act: -0.0000

Data Index: 1191174 (The Pile)

Max Activating Token Index: 1009