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

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

Neuron 4522 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4472. Min Range: -2.4472

Max Act: 2.4472. Min Act: -0.0000

Data Index: 1091524 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 2.4472. Min Range: -2.4472

Max Act: 2.3055. Min Act: -0.0000

Data Index: 227612 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 2.4472. Min Range: -2.4472

Max Act: 2.1886. Min Act: -0.0000

Data Index: 821062 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 2.4472. Min Range: -2.4472

Max Act: 1.9462. Min Act: -0.0000

Data Index: 1146100 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 2.4472. Min Range: -2.4472

Max Act: 2.0098. Min Act: -0.0000

Data Index: 1123857 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 2.4472. Min Range: -2.4472

Max Act: 1.8759. Min Act: -0.0000

Data Index: 756978 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 2.4472. Min Range: -2.4472

Max Act: 1.9648. Min Act: -0.0000

Data Index: 1317013 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 2.4472. Min Range: -2.4472

Max Act: 1.8246. Min Act: 0.0000

Data Index: 116906 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 2.4472. Min Range: -2.4472

Max Act: 1.9141. Min Act: -0.0000

Data Index: 1284046 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 2.4472. Min Range: -2.4472

Max Act: 1.8397. Min Act: -0.0000

Data Index: 1030896 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 2.4472. Min Range: -2.4472

Max Act: 1.8382. Min Act: -0.0000

Data Index: 203539 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 2.4472. Min Range: -2.4472

Max Act: 1.8514. Min Act: -0.0000

Data Index: 1316498 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 2.4472. Min Range: -2.4472

Max Act: 1.8090. Min Act: -0.0000

Data Index: 361144 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 2.4472. Min Range: -2.4472

Max Act: 1.4828. Min Act: -0.0000

Data Index: 6655 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 2.4472. Min Range: -2.4472

Max Act: 1.6068. Min Act: -0.0000

Data Index: 333012 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 2.4472. Min Range: -2.4472

Max Act: 1.5328. Min Act: -0.0000

Data Index: 502297 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 2.4472. Min Range: -2.4472

Max Act: 1.6924. Min Act: 0.0000

Data Index: 1221174 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 2.4472. Min Range: -2.4472

Max Act: 1.6834. Min Act: 0.0000

Data Index: 188359 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 2.4472. Min Range: -2.4472

Max Act: 1.6689. Min Act: 0.0000

Data Index: 1085245 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 2.4472. Min Range: -2.4472

Max Act: 1.6136. Min Act: 0.0000

Data Index: 431347 (C4 (Web Text))

Max Activating Token Index: 656