Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1850 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.1417. Min Range: -5.1417

Max Act: 5.1417. Min Act: -0.0001

Data Index: 882857 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 5.1417. Min Range: -5.1417

Max Act: 4.3986. Min Act: -0.0001

Data Index: 234229 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 5.1417. Min Range: -5.1417

Max Act: 4.1003. Min Act: -0.0001

Data Index: 890329 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 5.1417. Min Range: -5.1417

Max Act: 4.8721. Min Act: -0.0001

Data Index: 154140 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 5.1417. Min Range: -5.1417

Max Act: 3.9772. Min Act: -0.0001

Data Index: 540445 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 5.1417. Min Range: -5.1417

Max Act: 4.2912. Min Act: -0.0001

Data Index: 927956 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 5.1417. Min Range: -5.1417

Max Act: 4.0948. Min Act: -0.0001

Data Index: 882869 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 5.1417. Min Range: -5.1417

Max Act: 4.0245. Min Act: -0.0001

Data Index: 778165 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 5.1417. Min Range: -5.1417

Max Act: 3.9810. Min Act: -0.0001

Data Index: 1035618 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 5.1417. Min Range: -5.1417

Max Act: 3.6273. Min Act: -0.0001

Data Index: 645161 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 5.1417. Min Range: -5.1417

Max Act: 3.3586. Min Act: -0.0001

Data Index: 568206 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 5.1417. Min Range: -5.1417

Max Act: 3.7151. Min Act: -0.0001

Data Index: 719540 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 5.1417. Min Range: -5.1417

Max Act: 3.5355. Min Act: -0.0001

Data Index: 506528 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 5.1417. Min Range: -5.1417

Max Act: 3.6177. Min Act: -0.0001

Data Index: 1064857 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 5.1417. Min Range: -5.1417

Max Act: 3.5791. Min Act: -0.0001

Data Index: 713542 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 5.1417. Min Range: -5.1417

Max Act: 3.2654. Min Act: -0.0001

Data Index: 322822 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 5.1417. Min Range: -5.1417

Max Act: 3.5112. Min Act: -0.0001

Data Index: 595283 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 5.1417. Min Range: -5.1417

Max Act: 3.3630. Min Act: -0.0001

Data Index: 489909 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 5.1417. Min Range: -5.1417

Max Act: 3.8107. Min Act: -0.0001

Data Index: 796062 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 5.1417. Min Range: -5.1417

Max Act: 3.6897. Min Act: -0.0001

Data Index: 173872 (C4 (Web Text))

Max Activating Token Index: 633