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

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

Neuron 1483 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: 3.3167. Min Range: -3.3167

Max Act: 3.2215. Min Act: -0.0001

Data Index: 898597 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 3.3167. Min Range: -3.3167

Max Act: 3.3167. Min Act: -0.0001

Data Index: 997591 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 3.3167. Min Range: -3.3167

Max Act: 3.1416. Min Act: -0.0001

Data Index: 432229 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 3.3167. Min Range: -3.3167

Max Act: 2.9916. Min Act: -0.0000

Data Index: 353911 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 3.3167. Min Range: -3.3167

Max Act: 2.7165. Min Act: -0.0000

Data Index: 121132 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 3.3167. Min Range: -3.3167

Max Act: 2.8240. Min Act: -0.0001

Data Index: 257359 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 3.3167. Min Range: -3.3167

Max Act: 2.6183. Min Act: -0.0001

Data Index: 1350344 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 3.3167. Min Range: -3.3167

Max Act: 2.6877. Min Act: -0.0001

Data Index: 294511 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 3.3167. Min Range: -3.3167

Max Act: 2.6650. Min Act: -0.0001

Data Index: 733151 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 3.3167. Min Range: -3.3167

Max Act: 2.5302. Min Act: -0.0001

Data Index: 992373 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 3.3167. Min Range: -3.3167

Max Act: 2.5261. Min Act: -0.0000

Data Index: 132497 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 3.3167. Min Range: -3.3167

Max Act: 2.7627. Min Act: -0.0001

Data Index: 1121712 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 3.3167. Min Range: -3.3167

Max Act: 2.7451. Min Act: -0.0001

Data Index: 1164102 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 3.3167. Min Range: -3.3167

Max Act: 2.5672. Min Act: -0.0001

Data Index: 1098019 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 3.3167. Min Range: -3.3167

Max Act: 2.6824. Min Act: -0.0001

Data Index: 163048 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 3.3167. Min Range: -3.3167

Max Act: 2.4114. Min Act: -0.0001

Data Index: 372924 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 3.3167. Min Range: -3.3167

Max Act: 2.5414. Min Act: -0.0001

Data Index: 803895 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 3.3167. Min Range: -3.3167

Max Act: 2.4254. Min Act: -0.0001

Data Index: 567649 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 3.3167. Min Range: -3.3167

Max Act: 2.4813. Min Act: -0.0001

Data Index: 131736 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 3.3167. Min Range: -3.3167

Max Act: 2.7262. Min Act: -0.0001

Data Index: 1118189 (C4 (Web Text))

Max Activating Token Index: 81