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

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

Neuron 1169 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: 3.9800. Min Range: -3.9800

Max Act: 3.9800. Min Act: -0.0000

Data Index: 144193 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.6135. Min Act: -0.0001

Data Index: 1043550 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.4287. Min Act: -0.0000

Data Index: 48018 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.0792. Min Act: -0.0000

Data Index: 584209 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.1088. Min Act: -0.0001

Data Index: 412066 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 3.9800. Min Range: -3.9800

Max Act: 2.9673. Min Act: -0.0001

Data Index: 1265103 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 3.9800. Min Range: -3.9800

Max Act: 3.0833. Min Act: -0.0000

Data Index: 1105366 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 3.9800. Min Range: -3.9800

Max Act: 2.8854. Min Act: -0.0001

Data Index: 42742 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 3.9800. Min Range: -3.9800

Max Act: 2.7126. Min Act: -0.0001

Data Index: 527055 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 3.9800. Min Range: -3.9800

Max Act: 2.5264. Min Act: -0.0001

Data Index: 64793 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 3.9800. Min Range: -3.9800

Max Act: 2.5944. Min Act: -0.0001

Data Index: 1054199 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 3.9800. Min Range: -3.9800

Max Act: 2.4304. Min Act: -0.0001

Data Index: 1037072 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 3.9800. Min Range: -3.9800

Max Act: 2.6745. Min Act: -0.0000

Data Index: 84020 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 3.9800. Min Range: -3.9800

Max Act: 2.5477. Min Act: -0.0000

Data Index: 977856 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 3.9800. Min Range: -3.9800

Max Act: 2.5578. Min Act: -0.0001

Data Index: 236121 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 3.9800. Min Range: -3.9800

Max Act: 2.3676. Min Act: -0.0001

Data Index: 1110874 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 3.9800. Min Range: -3.9800

Max Act: 2.6080. Min Act: -0.0001

Data Index: 605419 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 3.9800. Min Range: -3.9800

Max Act: 2.4453. Min Act: -0.0001

Data Index: 492314 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 3.9800. Min Range: -3.9800

Max Act: 2.4218. Min Act: -0.0001

Data Index: 876199 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 3.9800. Min Range: -3.9800

Max Act: 2.4468. Min Act: -0.0000

Data Index: 209433 (C4 (Web Text))

Max Activating Token Index: 323