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

Dataset: The Pile

Neuron 3065 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.4256. Min Act: -0.0000

Data Index: 414059 (The Pile)

Max Activating Token Index: 547

Text #1

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.1475. Min Act: -0.0000

Data Index: 1200312 (The Pile)

Max Activating Token Index: 556

Text #2

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.0336. Min Act: -0.0000

Data Index: 1561755 (The Pile)

Max Activating Token Index: 547

Text #3

Max Range: 3.4256. Min Range: -3.4256

Max Act: 2.9952. Min Act: -0.0000

Data Index: 549260 (The Pile)

Max Activating Token Index: 143

Text #4

Max Range: 3.4256. Min Range: -3.4256

Max Act: 2.9797. Min Act: -0.0000

Data Index: 1652776 (The Pile)

Max Activating Token Index: 43

Text #5

Max Range: 3.4256. Min Range: -3.4256

Max Act: 2.9055. Min Act: -0.0000

Data Index: 938738 (The Pile)

Max Activating Token Index: 238

Text #6

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.0183. Min Act: -0.0000

Data Index: 494610 (The Pile)

Max Activating Token Index: 145

Text #7

Max Range: 3.4256. Min Range: -3.4256

Max Act: 2.7658. Min Act: -0.0000

Data Index: 162023 (The Pile)

Max Activating Token Index: 228

Text #8

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.0217. Min Act: -0.0000

Data Index: 304018 (The Pile)

Max Activating Token Index: 622

Text #9

Max Range: 3.4256. Min Range: -3.4256

Max Act: 2.8566. Min Act: -0.0000

Data Index: 889826 (The Pile)

Max Activating Token Index: 345

Text #10

Max Range: 3.4256. Min Range: -3.4256

Max Act: 2.8543. Min Act: -0.0000

Data Index: 1789913 (The Pile)

Max Activating Token Index: 564

Text #11

Max Range: 3.4256. Min Range: -3.4256

Max Act: 2.9322. Min Act: -0.0000

Data Index: 209609 (The Pile)

Max Activating Token Index: 602

Text #12

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.0445. Min Act: -0.0000

Data Index: 441955 (The Pile)

Max Activating Token Index: 377

Text #13

Max Range: 3.4256. Min Range: -3.4256

Max Act: 2.7079. Min Act: -0.0000

Data Index: 725350 (The Pile)

Max Activating Token Index: 418

Text #14

Max Range: 3.4256. Min Range: -3.4256

Max Act: 2.8692. Min Act: -0.0000

Data Index: 1049025 (The Pile)

Max Activating Token Index: 743

Text #15

Max Range: 3.4256. Min Range: -3.4256

Max Act: 2.8459. Min Act: -0.0000

Data Index: 1983269 (The Pile)

Max Activating Token Index: 440

Text #16

Max Range: 3.4256. Min Range: -3.4256

Max Act: 2.6855. Min Act: -0.0000

Data Index: 1951258 (The Pile)

Max Activating Token Index: 186

Text #17

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.0731. Min Act: -0.0000

Data Index: 1379210 (The Pile)

Max Activating Token Index: 248

Text #18

Max Range: 3.4256. Min Range: -3.4256

Max Act: 2.5997. Min Act: -0.0000

Data Index: 1305664 (The Pile)

Max Activating Token Index: 64

Text #19

Max Range: 3.4256. Min Range: -3.4256

Max Act: 2.7060. Min Act: -0.0000

Data Index: 883023 (The Pile)

Max Activating Token Index: 158