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

Dataset: The Pile

Neuron 2928 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.2951. Min Act: -0.0000

Data Index: 516276 (The Pile)

Max Activating Token Index: 982

Text #1

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.2430. Min Act: -0.0000

Data Index: 15933 (The Pile)

Max Activating Token Index: 641

Text #2

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.1731. Min Act: -0.0000

Data Index: 329587 (The Pile)

Max Activating Token Index: 378

Text #3

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.2178. Min Act: -0.0000

Data Index: 581925 (The Pile)

Max Activating Token Index: 792

Text #4

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.1468. Min Act: -0.0000

Data Index: 1086410 (The Pile)

Max Activating Token Index: 181

Text #5

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.1335. Min Act: -0.0000

Data Index: 1158272 (The Pile)

Max Activating Token Index: 914

Text #6

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.0745. Min Act: -0.0000

Data Index: 1548801 (The Pile)

Max Activating Token Index: 735

Text #7

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.1621. Min Act: -0.0000

Data Index: 887866 (The Pile)

Max Activating Token Index: 703

Text #8

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.0114. Min Act: -0.0000

Data Index: 309512 (The Pile)

Max Activating Token Index: 280

Text #9

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.0313. Min Act: -0.0000

Data Index: 195229 (The Pile)

Max Activating Token Index: 798

Text #10

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.0547. Min Act: -0.0000

Data Index: 1745557 (The Pile)

Max Activating Token Index: 138

Text #11

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.1002. Min Act: -0.0000

Data Index: 311860 (The Pile)

Max Activating Token Index: 768

Text #12

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.0104. Min Act: -0.0000

Data Index: 487474 (The Pile)

Max Activating Token Index: 298

Text #13

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.0288. Min Act: -0.0000

Data Index: 1111194 (The Pile)

Max Activating Token Index: 871

Text #14

Max Range: 1.2951. Min Range: -1.2951

Max Act: 0.9564. Min Act: -0.0000

Data Index: 226207 (The Pile)

Max Activating Token Index: 404

Text #15

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.0070. Min Act: -0.0000

Data Index: 1970245 (The Pile)

Max Activating Token Index: 412

Text #16

Max Range: 1.2951. Min Range: -1.2951

Max Act: 0.9957. Min Act: -0.0000

Data Index: 735911 (The Pile)

Max Activating Token Index: 928

Text #17

Max Range: 1.2951. Min Range: -1.2951

Max Act: 0.9939. Min Act: -0.0000

Data Index: 1123923 (The Pile)

Max Activating Token Index: 483

Text #18

Max Range: 1.2951. Min Range: -1.2951

Max Act: 0.9333. Min Act: -0.0000

Data Index: 1652001 (The Pile)

Max Activating Token Index: 234

Text #19

Max Range: 1.2951. Min Range: -1.2951

Max Act: 1.0581. Min Act: -0.0000

Data Index: 923768 (The Pile)

Max Activating Token Index: 797