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

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

Neuron 2774 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2474. Min Range: -2.2474

Max Act: 2.2474. Min Act: -0.0000

Data Index: 802022 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 2.2474. Min Range: -2.2474

Max Act: 2.1278. Min Act: -0.0000

Data Index: 111185 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 2.2474. Min Range: -2.2474

Max Act: 2.0737. Min Act: -0.0000

Data Index: 19319 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 2.2474. Min Range: -2.2474

Max Act: 2.0095. Min Act: -0.0000

Data Index: 874199 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.8849. Min Act: -0.0000

Data Index: 1349006 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.9419. Min Act: -0.0000

Data Index: 893878 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.8278. Min Act: -0.0000

Data Index: 364388 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 2.2474. Min Range: -2.2474

Max Act: 2.1294. Min Act: -0.0000

Data Index: 32360 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.9137. Min Act: -0.0000

Data Index: 17294 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.9066. Min Act: -0.0000

Data Index: 489926 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.9035. Min Act: -0.0000

Data Index: 531650 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.8749. Min Act: -0.0000

Data Index: 244131 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.8613. Min Act: -0.0000

Data Index: 45758 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.8419. Min Act: -0.0000

Data Index: 679222 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.7210. Min Act: -0.0000

Data Index: 150940 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.8262. Min Act: -0.0000

Data Index: 63111 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.9173. Min Act: -0.0000

Data Index: 572905 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.7066. Min Act: -0.0000

Data Index: 1185476 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.8998. Min Act: -0.0000

Data Index: 304112 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 2.2474. Min Range: -2.2474

Max Act: 1.7956. Min Act: -0.0000

Data Index: 1011960 (C4 (Web Text))

Max Activating Token Index: 98