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

Dataset: The Pile

Neuron 3877 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.6114. Min Act: -0.0000

Data Index: 1133898 (The Pile)

Max Activating Token Index: 403

Text #1

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.5485. Min Act: -0.0000

Data Index: 384431 (The Pile)

Max Activating Token Index: 64

Text #2

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.5356. Min Act: -0.0000

Data Index: 656999 (The Pile)

Max Activating Token Index: 699

Text #3

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1616571 (The Pile)

Max Activating Token Index: 515

Text #4

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4652. Min Act: -0.0000

Data Index: 221876 (The Pile)

Max Activating Token Index: 588

Text #5

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4916. Min Act: -0.0000

Data Index: 162144 (The Pile)

Max Activating Token Index: 97

Text #6

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4671. Min Act: -0.0000

Data Index: 614122 (The Pile)

Max Activating Token Index: 864

Text #7

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1641089 (The Pile)

Max Activating Token Index: 835

Text #8

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1853079 (The Pile)

Max Activating Token Index: 202

Text #9

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1157697 (The Pile)

Max Activating Token Index: 352

Text #10

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4306. Min Act: -0.0000

Data Index: 420475 (The Pile)

Max Activating Token Index: 403

Text #11

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4136. Min Act: -0.0000

Data Index: 590197 (The Pile)

Max Activating Token Index: 718

Text #12

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4345. Min Act: -0.0000

Data Index: 1878656 (The Pile)

Max Activating Token Index: 228

Text #13

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4076. Min Act: -0.0000

Data Index: 195734 (The Pile)

Max Activating Token Index: 585

Text #14

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.3731. Min Act: -0.0000

Data Index: 980361 (The Pile)

Max Activating Token Index: 275

Text #15

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.3915. Min Act: -0.0000

Data Index: 284539 (The Pile)

Max Activating Token Index: 58

Text #16

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4048. Min Act: -0.0000

Data Index: 188668 (The Pile)

Max Activating Token Index: 704

Text #17

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.4062. Min Act: -0.0000

Data Index: 12451 (The Pile)

Max Activating Token Index: 650

Text #18

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.3724. Min Act: -0.0000

Data Index: 310558 (The Pile)

Max Activating Token Index: 1020

Text #19

Max Range: 0.6114. Min Range: -0.6114

Max Act: 0.3446. Min Act: -0.0000

Data Index: 397450 (The Pile)

Max Activating Token Index: 248