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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3688 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6012. Min Range: -2.6012

Max Act: 2.6012. Min Act: -0.0000

Data Index: 719114 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 2.6012. Min Range: -2.6012

Max Act: 2.1362. Min Act: -0.0000

Data Index: 496109 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 2.6012. Min Range: -2.6012

Max Act: 2.1148. Min Act: -0.0000

Data Index: 134201 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 2.6012. Min Range: -2.6012

Max Act: 1.9827. Min Act: -0.0000

Data Index: 207257 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 2.6012. Min Range: -2.6012

Max Act: 1.7729. Min Act: -0.0000

Data Index: 860777 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 2.6012. Min Range: -2.6012

Max Act: 1.8543. Min Act: -0.0000

Data Index: 1166511 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 2.6012. Min Range: -2.6012

Max Act: 1.7673. Min Act: -0.0000

Data Index: 946574 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 2.6012. Min Range: -2.6012

Max Act: 1.7679. Min Act: -0.0000

Data Index: 868081 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 2.6012. Min Range: -2.6012

Max Act: 1.6367. Min Act: -0.0000

Data Index: 527782 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 2.6012. Min Range: -2.6012

Max Act: 1.7052. Min Act: -0.0000

Data Index: 920904 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 2.6012. Min Range: -2.6012

Max Act: 1.4037. Min Act: -0.0000

Data Index: 325435 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 2.6012. Min Range: -2.6012

Max Act: 1.6657. Min Act: -0.0000

Data Index: 213883 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 2.6012. Min Range: -2.6012

Max Act: 1.6656. Min Act: -0.0000

Data Index: 299050 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 2.6012. Min Range: -2.6012

Max Act: 1.6562. Min Act: -0.0000

Data Index: 1040305 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 2.6012. Min Range: -2.6012

Max Act: 1.7364. Min Act: -0.0000

Data Index: 1045794 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 2.6012. Min Range: -2.6012

Max Act: 1.6477. Min Act: -0.0000

Data Index: 962542 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 2.6012. Min Range: -2.6012

Max Act: 1.6309. Min Act: -0.0000

Data Index: 365293 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 2.6012. Min Range: -2.6012

Max Act: 1.6327. Min Act: -0.0000

Data Index: 1309358 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 2.6012. Min Range: -2.6012

Max Act: 1.6180. Min Act: -0.0000

Data Index: 422234 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 2.6012. Min Range: -2.6012

Max Act: 1.6144. Min Act: -0.0000

Data Index: 257482 (C4 (Web Text))

Max Activating Token Index: 118