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

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

Neuron 1985 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8936. Min Range: -2.8936

Max Act: 2.8220. Min Act: -0.0000

Data Index: 186484 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 2.8936. Min Range: -2.8936

Max Act: 2.8936. Min Act: -0.0000

Data Index: 718212 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 2.8936. Min Range: -2.8936

Max Act: 2.7908. Min Act: -0.0000

Data Index: 313077 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 2.8936. Min Range: -2.8936

Max Act: 2.7769. Min Act: -0.0000

Data Index: 528185 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 2.8936. Min Range: -2.8936

Max Act: 2.5305. Min Act: -0.0000

Data Index: 757401 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 2.8936. Min Range: -2.8936

Max Act: 2.5278. Min Act: -0.0000

Data Index: 1091903 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 2.8936. Min Range: -2.8936

Max Act: 2.7729. Min Act: -0.0000

Data Index: 963059 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 2.8936. Min Range: -2.8936

Max Act: 2.4891. Min Act: -0.0000

Data Index: 1338148 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 2.8936. Min Range: -2.8936

Max Act: 2.4331. Min Act: -0.0000

Data Index: 1202702 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 2.8936. Min Range: -2.8936

Max Act: 2.5571. Min Act: -0.0000

Data Index: 191925 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 2.8936. Min Range: -2.8936

Max Act: 2.5238. Min Act: -0.0000

Data Index: 1156970 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 2.8936. Min Range: -2.8936

Max Act: 2.5119. Min Act: -0.0000

Data Index: 756303 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 2.8936. Min Range: -2.8936

Max Act: 2.4999. Min Act: -0.0000

Data Index: 1018607 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 2.8936. Min Range: -2.8936

Max Act: 2.4922. Min Act: -0.0000

Data Index: 826350 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 2.8936. Min Range: -2.8936

Max Act: 2.6196. Min Act: -0.0000

Data Index: 700496 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 2.8936. Min Range: -2.8936

Max Act: 2.4964. Min Act: -0.0000

Data Index: 542189 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 2.8936. Min Range: -2.8936

Max Act: 2.4748. Min Act: -0.0000

Data Index: 665529 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 2.8936. Min Range: -2.8936

Max Act: 2.4737. Min Act: -0.0000

Data Index: 477340 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 2.8936. Min Range: -2.8936

Max Act: 2.4764. Min Act: -0.0000

Data Index: 1209200 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 2.8936. Min Range: -2.8936

Max Act: 2.3222. Min Act: -0.0000

Data Index: 706752 (C4 (Web Text))

Max Activating Token Index: 749