Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3132 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 5.0942. Min Range: -5.0942

Max Act: 5.0942. Min Act: -0.0000

Data Index: 819399 (The Pile)

Max Activating Token Index: 589

Text #1

Max Range: 5.0942. Min Range: -5.0942

Max Act: 5.0229. Min Act: -0.0000

Data Index: 925119 (The Pile)

Max Activating Token Index: 344

Text #2

Max Range: 5.0942. Min Range: -5.0942

Max Act: 4.7947. Min Act: -0.0000

Data Index: 777409 (The Pile)

Max Activating Token Index: 828

Text #3

Max Range: 5.0942. Min Range: -5.0942

Max Act: 4.7546. Min Act: -0.0000

Data Index: 80199 (The Pile)

Max Activating Token Index: 14

Text #4

Max Range: 5.0942. Min Range: -5.0942

Max Act: 4.9378. Min Act: -0.0000

Data Index: 1285397 (The Pile)

Max Activating Token Index: 469

Text #5

Max Range: 5.0942. Min Range: -5.0942

Max Act: 5.0645. Min Act: -0.0000

Data Index: 1503149 (The Pile)

Max Activating Token Index: 21

Text #6

Max Range: 5.0942. Min Range: -5.0942

Max Act: 4.8500. Min Act: -0.0000

Data Index: 1632256 (The Pile)

Max Activating Token Index: 201

Text #7

Max Range: 5.0942. Min Range: -5.0942

Max Act: 4.8179. Min Act: -0.0000

Data Index: 310826 (The Pile)

Max Activating Token Index: 22

Text #8

Max Range: 5.0942. Min Range: -5.0942

Max Act: 4.7842. Min Act: -0.0000

Data Index: 1603852 (The Pile)

Max Activating Token Index: 23

Text #9

Max Range: 5.0942. Min Range: -5.0942

Max Act: 4.7426. Min Act: -0.0000

Data Index: 1981000 (The Pile)

Max Activating Token Index: 60

Text #10

Max Range: 5.0942. Min Range: -5.0942

Max Act: 4.7152. Min Act: -0.0000

Data Index: 820189 (The Pile)

Max Activating Token Index: 413

Text #11

Max Range: 5.0942. Min Range: -5.0942

Max Act: 4.6898. Min Act: -0.0000

Data Index: 1659308 (The Pile)

Max Activating Token Index: 21

Text #12

Max Range: 5.0942. Min Range: -5.0942

Max Act: 4.5150. Min Act: -0.0000

Data Index: 644471 (The Pile)

Max Activating Token Index: 1009

Text #13

Max Range: 5.0942. Min Range: -5.0942

Max Act: 4.6629. Min Act: -0.0000

Data Index: 26247 (The Pile)

Max Activating Token Index: 370

Text #14

Max Range: 5.0942. Min Range: -5.0942

Max Act: 4.6735. Min Act: -0.0000

Data Index: 865717 (The Pile)

Max Activating Token Index: 14

Text #15

Max Range: 5.0942. Min Range: -5.0942

Max Act: 4.7084. Min Act: -0.0000

Data Index: 841178 (The Pile)

Max Activating Token Index: 749

Text #16

Max Range: 5.0942. Min Range: -5.0942

Max Act: 4.6715. Min Act: -0.0000

Data Index: 1008890 (The Pile)

Max Activating Token Index: 16

Text #17

Max Range: 5.0942. Min Range: -5.0942

Max Act: 4.6665. Min Act: -0.0000

Data Index: 618340 (The Pile)

Max Activating Token Index: 721

Text #18

Max Range: 5.0942. Min Range: -5.0942

Max Act: 4.6505. Min Act: -0.0000

Data Index: 421280 (The Pile)

Max Activating Token Index: 20

Text #19

Max Range: 5.0942. Min Range: -5.0942

Max Act: 4.6098. Min Act: -0.0000

Data Index: 1377887 (The Pile)

Max Activating Token Index: 64