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

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

Neuron 1791 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.0417. Min Range: -10.0417

Max Act: 10.0417. Min Act: -0.0000

Data Index: 119132 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 10.0417. Min Range: -10.0417

Max Act: 8.9041. Min Act: -0.0000

Data Index: 1333325 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 10.0417. Min Range: -10.0417

Max Act: 8.7151. Min Act: -0.0000

Data Index: 525051 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 10.0417. Min Range: -10.0417

Max Act: 8.6028. Min Act: -0.0000

Data Index: 100657 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 10.0417. Min Range: -10.0417

Max Act: 8.4651. Min Act: -0.0000

Data Index: 708585 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 10.0417. Min Range: -10.0417

Max Act: 8.5499. Min Act: -0.0000

Data Index: 263963 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 10.0417. Min Range: -10.0417

Max Act: 8.1498. Min Act: -0.0000

Data Index: 155209 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 10.0417. Min Range: -10.0417

Max Act: 7.8009. Min Act: -0.0000

Data Index: 480845 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 10.0417. Min Range: -10.0417

Max Act: 8.4556. Min Act: -0.0000

Data Index: 1070471 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 10.0417. Min Range: -10.0417

Max Act: 8.1257. Min Act: -0.0000

Data Index: 1196296 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 10.0417. Min Range: -10.0417

Max Act: 8.0226. Min Act: -0.0000

Data Index: 11686 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 10.0417. Min Range: -10.0417

Max Act: 8.1578. Min Act: -0.0000

Data Index: 813593 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 10.0417. Min Range: -10.0417

Max Act: 8.1067. Min Act: -0.0000

Data Index: 717067 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 10.0417. Min Range: -10.0417

Max Act: 8.1154. Min Act: -0.0000

Data Index: 918686 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 10.0417. Min Range: -10.0417

Max Act: 7.5746. Min Act: -0.0000

Data Index: 428087 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 10.0417. Min Range: -10.0417

Max Act: 8.0521. Min Act: -0.0000

Data Index: 66998 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 10.0417. Min Range: -10.0417

Max Act: 7.4872. Min Act: -0.0000

Data Index: 705781 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 10.0417. Min Range: -10.0417

Max Act: 7.7947. Min Act: -0.0000

Data Index: 345461 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 10.0417. Min Range: -10.0417

Max Act: 7.5333. Min Act: -0.0000

Data Index: 918608 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 10.0417. Min Range: -10.0417

Max Act: 7.3748. Min Act: -0.0000

Data Index: 469665 (C4 (Web Text))

Max Activating Token Index: 407