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

Dataset: The Pile

Neuron 2943 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: 1.6818. Min Range: -1.6818

Max Act: 1.6818. Min Act: -0.0000

Data Index: 1290363 (The Pile)

Max Activating Token Index: 885

Text #1

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.5670. Min Act: -0.0000

Data Index: 1547996 (The Pile)

Max Activating Token Index: 69

Text #2

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.5225. Min Act: -0.0000

Data Index: 1558292 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.5442. Min Act: -0.0000

Data Index: 30114 (The Pile)

Max Activating Token Index: 950

Text #4

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.4575. Min Act: -0.0000

Data Index: 131902 (The Pile)

Max Activating Token Index: 878

Text #5

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.5317. Min Act: -0.0000

Data Index: 752944 (The Pile)

Max Activating Token Index: 526

Text #6

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.5284. Min Act: -0.0000

Data Index: 1414168 (The Pile)

Max Activating Token Index: 974

Text #7

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.5635. Min Act: -0.0000

Data Index: 1568438 (The Pile)

Max Activating Token Index: 535

Text #8

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.3653. Min Act: -0.0000

Data Index: 1938541 (The Pile)

Max Activating Token Index: 956

Text #9

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.5388. Min Act: -0.0000

Data Index: 515449 (The Pile)

Max Activating Token Index: 582

Text #10

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.5123. Min Act: -0.0000

Data Index: 298758 (The Pile)

Max Activating Token Index: 110

Text #11

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.4295. Min Act: -0.0000

Data Index: 1111202 (The Pile)

Max Activating Token Index: 184

Text #12

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.4300. Min Act: -0.0000

Data Index: 1168184 (The Pile)

Max Activating Token Index: 47

Text #13

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.4112. Min Act: -0.0000

Data Index: 599820 (The Pile)

Max Activating Token Index: 621

Text #14

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.3302. Min Act: -0.0000

Data Index: 249735 (The Pile)

Max Activating Token Index: 915

Text #15

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.4143. Min Act: -0.0000

Data Index: 755555 (The Pile)

Max Activating Token Index: 91

Text #16

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.4072. Min Act: -0.0000

Data Index: 1509432 (The Pile)

Max Activating Token Index: 615

Text #17

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.3275. Min Act: -0.0000

Data Index: 1655962 (The Pile)

Max Activating Token Index: 898

Text #18

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.4078. Min Act: -0.0000

Data Index: 179877 (The Pile)

Max Activating Token Index: 17

Text #19

Max Range: 1.6818. Min Range: -1.6818

Max Act: 1.4728. Min Act: -0.0000

Data Index: 1289440 (The Pile)

Max Activating Token Index: 968