Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3125 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1330. Min Act: -0.0002

Data Index: 329943 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1096. Min Act: -0.0002

Data Index: 218259 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0947. Min Act: -0.0001

Data Index: 1051211 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0817. Min Act: -0.0001

Data Index: 276968 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0679. Min Act: -0.0001

Data Index: 132882 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0712. Min Act: -0.0001

Data Index: 953819 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0567. Min Act: -0.0002

Data Index: 980481 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0549. Min Act: -0.0001

Data Index: 1357910 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0491. Min Act: -0.0001

Data Index: 710799 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0503. Min Act: -0.0001

Data Index: 1341409 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0502. Min Act: -0.0002

Data Index: 818754 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0478. Min Act: -0.0002

Data Index: 225788 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0577. Min Act: -0.0001

Data Index: 842228 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0491. Min Act: -0.0001

Data Index: 347496 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0358. Min Act: -0.0002

Data Index: 1085275 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0452. Min Act: -0.0002

Data Index: 744670 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0439. Min Act: -0.0001

Data Index: 35157 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0475. Min Act: -0.0001

Data Index: 1147150 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1232267 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0446. Min Act: -0.0001

Data Index: 372370 (C4 (Web Text))

Max Activating Token Index: 156