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

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

Neuron 2842 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: 0.6295. Min Range: -0.6295

Max Act: 0.6295. Min Act: -0.0000

Data Index: 787923 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.5552. Min Act: -0.0000

Data Index: 734994 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1231287 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.5566. Min Act: -0.0000

Data Index: 504670 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.5100. Min Act: -0.0000

Data Index: 543250 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.5008. Min Act: -0.0000

Data Index: 93802 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.4859. Min Act: -0.0000

Data Index: 738687 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.4868. Min Act: -0.0000

Data Index: 963877 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.4930. Min Act: -0.0000

Data Index: 321670 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.4927. Min Act: -0.0000

Data Index: 486478 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.4710. Min Act: -0.0000

Data Index: 941973 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.4404. Min Act: -0.0000

Data Index: 166443 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.4531. Min Act: -0.0000

Data Index: 927723 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.4796. Min Act: -0.0000

Data Index: 60316 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.4292. Min Act: -0.0000

Data Index: 638192 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.4454. Min Act: -0.0000

Data Index: 1032539 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.4190. Min Act: -0.0000

Data Index: 178930 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.4220. Min Act: -0.0000

Data Index: 810753 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.4228. Min Act: -0.0000

Data Index: 482845 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 0.6295. Min Range: -0.6295

Max Act: 0.3993. Min Act: -0.0000

Data Index: 147488 (C4 (Web Text))

Max Activating Token Index: 563