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

Dataset: The Pile

Neuron 542 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: 10.7864. Min Range: -10.7864

Max Act: 10.7864. Min Act: -0.0000

Data Index: 1328253 (The Pile)

Max Activating Token Index: 337

Text #1

Max Range: 10.7864. Min Range: -10.7864

Max Act: 10.4198. Min Act: -0.0000

Data Index: 395615 (The Pile)

Max Activating Token Index: 584

Text #2

Max Range: 10.7864. Min Range: -10.7864

Max Act: 10.4253. Min Act: -0.0000

Data Index: 406492 (The Pile)

Max Activating Token Index: 163

Text #3

Max Range: 10.7864. Min Range: -10.7864

Max Act: 10.6826. Min Act: -0.0000

Data Index: 1966388 (The Pile)

Max Activating Token Index: 763

Text #4

Max Range: 10.7864. Min Range: -10.7864

Max Act: 10.1003. Min Act: -0.0000

Data Index: 1801233 (The Pile)

Max Activating Token Index: 207

Text #5

Max Range: 10.7864. Min Range: -10.7864

Max Act: 9.8108. Min Act: -0.0000

Data Index: 269639 (The Pile)

Max Activating Token Index: 710

Text #6

Max Range: 10.7864. Min Range: -10.7864

Max Act: 9.3858. Min Act: -0.0000

Data Index: 225930 (The Pile)

Max Activating Token Index: 317

Text #7

Max Range: 10.7864. Min Range: -10.7864

Max Act: 9.9214. Min Act: -0.0000

Data Index: 1410703 (The Pile)

Max Activating Token Index: 244

Text #8

Max Range: 10.7864. Min Range: -10.7864

Max Act: 9.4318. Min Act: -0.0000

Data Index: 806091 (The Pile)

Max Activating Token Index: 231

Text #9

Max Range: 10.7864. Min Range: -10.7864

Max Act: 9.3777. Min Act: -0.0000

Data Index: 698251 (The Pile)

Max Activating Token Index: 374

Text #10

Max Range: 10.7864. Min Range: -10.7864

Max Act: 9.0259. Min Act: -0.0000

Data Index: 1733216 (The Pile)

Max Activating Token Index: 664

Text #11

Max Range: 10.7864. Min Range: -10.7864

Max Act: 9.1735. Min Act: -0.0000

Data Index: 531687 (The Pile)

Max Activating Token Index: 374

Text #12

Max Range: 10.7864. Min Range: -10.7864

Max Act: 9.1909. Min Act: -0.0000

Data Index: 1045479 (The Pile)

Max Activating Token Index: 113

Text #13

Max Range: 10.7864. Min Range: -10.7864

Max Act: 8.9804. Min Act: -0.0000

Data Index: 406262 (The Pile)

Max Activating Token Index: 222

Text #14

Max Range: 10.7864. Min Range: -10.7864

Max Act: 8.9085. Min Act: -0.0000

Data Index: 1402383 (The Pile)

Max Activating Token Index: 624

Text #15

Max Range: 10.7864. Min Range: -10.7864

Max Act: 8.8942. Min Act: -0.0000

Data Index: 196601 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 10.7864. Min Range: -10.7864

Max Act: 8.8884. Min Act: -0.0000

Data Index: 1878253 (The Pile)

Max Activating Token Index: 840

Text #17

Max Range: 10.7864. Min Range: -10.7864

Max Act: 8.3479. Min Act: -0.0000

Data Index: 83435 (The Pile)

Max Activating Token Index: 219

Text #18

Max Range: 10.7864. Min Range: -10.7864

Max Act: 8.8165. Min Act: -0.0000

Data Index: 987795 (The Pile)

Max Activating Token Index: 699

Text #19

Max Range: 10.7864. Min Range: -10.7864

Max Act: 8.6969. Min Act: -0.0000

Data Index: 1441248 (The Pile)

Max Activating Token Index: 481