Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 482 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.7294. Min Act: -0.0001

Data Index: 672864 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.6584. Min Act: -0.0001

Data Index: 1165576 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.6341. Min Act: -0.0000

Data Index: 1082691 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5882. Min Act: -0.0001

Data Index: 406830 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5631. Min Act: -0.0001

Data Index: 1003829 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5800. Min Act: -0.0001

Data Index: 632046 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5705. Min Act: -0.0001

Data Index: 1085291 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.6032. Min Act: -0.0001

Data Index: 934042 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5934. Min Act: -0.0001

Data Index: 300252 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5669. Min Act: -0.0001

Data Index: 1005113 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5390. Min Act: -0.0001

Data Index: 365885 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5912. Min Act: -0.0001

Data Index: 785214 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5714. Min Act: -0.0000

Data Index: 736807 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.4973. Min Act: -0.0001

Data Index: 971431 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5255. Min Act: -0.0001

Data Index: 438208 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5035. Min Act: -0.0001

Data Index: 1083752 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5219. Min Act: -0.0001

Data Index: 260144 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5123. Min Act: -0.0001

Data Index: 216739 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5626. Min Act: -0.0001

Data Index: 422863 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.7294. Min Range: -0.7294

Max Act: 0.5136. Min Act: -0.0001

Data Index: 1139298 (C4 (Web Text))

Max Activating Token Index: 528