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

Dataset: The Pile

Neuron 3818 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: 0.6367. Min Range: -0.6367

Max Act: 0.6090. Min Act: -0.0000

Data Index: 214970 (The Pile)

Max Activating Token Index: 473

Text #1

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.6367. Min Act: -0.0000

Data Index: 587383 (The Pile)

Max Activating Token Index: 193

Text #2

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.6126. Min Act: -0.0000

Data Index: 998073 (The Pile)

Max Activating Token Index: 139

Text #3

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.5846. Min Act: -0.0000

Data Index: 1240808 (The Pile)

Max Activating Token Index: 46

Text #4

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.5768. Min Act: -0.0000

Data Index: 1136570 (The Pile)

Max Activating Token Index: 303

Text #5

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.5632. Min Act: -0.0000

Data Index: 239670 (The Pile)

Max Activating Token Index: 395

Text #6

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.5791. Min Act: -0.0000

Data Index: 1314531 (The Pile)

Max Activating Token Index: 219

Text #7

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1519079 (The Pile)

Max Activating Token Index: 450

Text #8

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1540909 (The Pile)

Max Activating Token Index: 373

Text #9

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1387287 (The Pile)

Max Activating Token Index: 61

Text #10

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.5043. Min Act: -0.0000

Data Index: 1463464 (The Pile)

Max Activating Token Index: 326

Text #11

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.4553. Min Act: -0.0000

Data Index: 1463409 (The Pile)

Max Activating Token Index: 616

Text #12

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.5161. Min Act: -0.0000

Data Index: 859397 (The Pile)

Max Activating Token Index: 996

Text #13

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1762995 (The Pile)

Max Activating Token Index: 741

Text #14

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.5059. Min Act: -0.0000

Data Index: 1894700 (The Pile)

Max Activating Token Index: 537

Text #15

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.5043. Min Act: -0.0000

Data Index: 1187012 (The Pile)

Max Activating Token Index: 981

Text #16

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.4963. Min Act: -0.0000

Data Index: 1184274 (The Pile)

Max Activating Token Index: 1016

Text #17

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.4841. Min Act: -0.0000

Data Index: 1357660 (The Pile)

Max Activating Token Index: 59

Text #18

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.4978. Min Act: -0.0000

Data Index: 1549497 (The Pile)

Max Activating Token Index: 884

Text #19

Max Range: 0.6367. Min Range: -0.6367

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1755207 (The Pile)

Max Activating Token Index: 395