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

Dataset: The Pile

Neuron 2926 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.1383. Min Act: -0.0000

Data Index: 1232576 (The Pile)

Max Activating Token Index: 473

Text #1

Max Range: 1.1400. Min Range: -1.1400

Max Act: 1.1400. Min Act: -0.0000

Data Index: 148970 (The Pile)

Max Activating Token Index: 223

Text #2

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.9404. Min Act: -0.0000

Data Index: 1064014 (The Pile)

Max Activating Token Index: 969

Text #3

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.9375. Min Act: -0.0000

Data Index: 1505598 (The Pile)

Max Activating Token Index: 842

Text #4

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.8996. Min Act: -0.0000

Data Index: 551353 (The Pile)

Max Activating Token Index: 708

Text #5

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.9086. Min Act: -0.0000

Data Index: 1619019 (The Pile)

Max Activating Token Index: 115

Text #6

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.8584. Min Act: -0.0000

Data Index: 288230 (The Pile)

Max Activating Token Index: 889

Text #7

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.9060. Min Act: -0.0000

Data Index: 494949 (The Pile)

Max Activating Token Index: 921

Text #8

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.8833. Min Act: -0.0000

Data Index: 924733 (The Pile)

Max Activating Token Index: 497

Text #9

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.8250. Min Act: -0.0000

Data Index: 235615 (The Pile)

Max Activating Token Index: 818

Text #10

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.9092. Min Act: -0.0000

Data Index: 1492893 (The Pile)

Max Activating Token Index: 691

Text #11

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.7556. Min Act: -0.0000

Data Index: 62273 (The Pile)

Max Activating Token Index: 276

Text #12

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.7674. Min Act: -0.0000

Data Index: 1812421 (The Pile)

Max Activating Token Index: 852

Text #13

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.8062. Min Act: -0.0000

Data Index: 1927189 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.8190. Min Act: -0.0000

Data Index: 1778795 (The Pile)

Max Activating Token Index: 301

Text #15

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.7997. Min Act: -0.0000

Data Index: 1223477 (The Pile)

Max Activating Token Index: 86

Text #16

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.7637. Min Act: -0.0000

Data Index: 743654 (The Pile)

Max Activating Token Index: 732

Text #17

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.7536. Min Act: -0.0000

Data Index: 142562 (The Pile)

Max Activating Token Index: 192

Text #18

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.7713. Min Act: -0.0000

Data Index: 1385009 (The Pile)

Max Activating Token Index: 136

Text #19

Max Range: 1.1400. Min Range: -1.1400

Max Act: 0.8037. Min Act: -0.0000

Data Index: 726620 (The Pile)

Max Activating Token Index: 368