Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2331 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.5833. Min Act: -0.0001

Data Index: 546703 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.6201. Min Act: -0.0001

Data Index: 185661 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.4259. Min Act: -0.0001

Data Index: 30120 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.4467. Min Act: -0.0001

Data Index: 664175 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.5386. Min Act: -0.0001

Data Index: 423000 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.3944. Min Act: -0.0001

Data Index: 131850 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.5069. Min Act: -0.0001

Data Index: 1094693 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.4278. Min Act: -0.0001

Data Index: 35859 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.4093. Min Act: -0.0001

Data Index: 976903 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.3641. Min Act: -0.0001

Data Index: 1254565 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.3409. Min Act: -0.0001

Data Index: 528022 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.3832. Min Act: -0.0001

Data Index: 531449 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.3756. Min Act: -0.0001

Data Index: 890521 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.3654. Min Act: -0.0001

Data Index: 648992 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.3611. Min Act: -0.0001

Data Index: 587437 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.4248. Min Act: -0.0001

Data Index: 16518 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.3427. Min Act: -0.0001

Data Index: 356928 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.3404. Min Act: -0.0001

Data Index: 700616 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.3110. Min Act: -0.0001

Data Index: 645219 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.2568. Min Act: -0.0001

Data Index: 1307031 (C4 (Web Text))

Max Activating Token Index: 941