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

Dataset: The Pile

Neuron 1231 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1865. Min Range: -3.1865

Max Act: 3.1865. Min Act: -0.0000

Data Index: 671237 (The Pile)

Max Activating Token Index: 219

Text #1

Max Range: 3.1865. Min Range: -3.1865

Max Act: 3.1245. Min Act: -0.0000

Data Index: 933109 (The Pile)

Max Activating Token Index: 354

Text #2

Max Range: 3.1865. Min Range: -3.1865

Max Act: 3.0880. Min Act: -0.0000

Data Index: 1962291 (The Pile)

Max Activating Token Index: 330

Text #3

Max Range: 3.1865. Min Range: -3.1865

Max Act: 3.0792. Min Act: -0.0000

Data Index: 451068 (The Pile)

Max Activating Token Index: 118

Text #4

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.8339. Min Act: -0.0000

Data Index: 113115 (The Pile)

Max Activating Token Index: 305

Text #5

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.8361. Min Act: -0.0000

Data Index: 507388 (The Pile)

Max Activating Token Index: 425

Text #6

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.9170. Min Act: -0.0000

Data Index: 1308395 (The Pile)

Max Activating Token Index: 244

Text #7

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.7528. Min Act: -0.0000

Data Index: 1078230 (The Pile)

Max Activating Token Index: 631

Text #8

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.7150. Min Act: -0.0000

Data Index: 251444 (The Pile)

Max Activating Token Index: 624

Text #9

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.8799. Min Act: -0.0000

Data Index: 600949 (The Pile)

Max Activating Token Index: 413

Text #10

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.5642. Min Act: -0.0000

Data Index: 153170 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.8449. Min Act: -0.0000

Data Index: 1776419 (The Pile)

Max Activating Token Index: 215

Text #12

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.7052. Min Act: -0.0000

Data Index: 522599 (The Pile)

Max Activating Token Index: 269

Text #13

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.8266. Min Act: -0.0000

Data Index: 908270 (The Pile)

Max Activating Token Index: 325

Text #14

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.6841. Min Act: -0.0000

Data Index: 650189 (The Pile)

Max Activating Token Index: 311

Text #15

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.8399. Min Act: -0.0000

Data Index: 922016 (The Pile)

Max Activating Token Index: 473

Text #16

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.8371. Min Act: -0.0000

Data Index: 1634018 (The Pile)

Max Activating Token Index: 531

Text #17

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.5445. Min Act: -0.0000

Data Index: 1192772 (The Pile)

Max Activating Token Index: 619

Text #18

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.7700. Min Act: -0.0000

Data Index: 887145 (The Pile)

Max Activating Token Index: 461

Text #19

Max Range: 3.1865. Min Range: -3.1865

Max Act: 2.7781. Min Act: -0.0000

Data Index: 1639884 (The Pile)

Max Activating Token Index: 511