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

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

Neuron 819 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: 4.0114. Min Range: -4.0114

Max Act: 3.8999. Min Act: -0.0001

Data Index: 445789 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 4.0114. Min Range: -4.0114

Max Act: 4.0114. Min Act: -0.0001

Data Index: 40383 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 4.0114. Min Range: -4.0114

Max Act: 3.7224. Min Act: -0.0001

Data Index: 284010 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 4.0114. Min Range: -4.0114

Max Act: 3.4589. Min Act: -0.0001

Data Index: 457899 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 4.0114. Min Range: -4.0114

Max Act: 3.5927. Min Act: -0.0001

Data Index: 1172380 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 4.0114. Min Range: -4.0114

Max Act: 3.4796. Min Act: -0.0001

Data Index: 825562 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 4.0114. Min Range: -4.0114

Max Act: 3.1766. Min Act: -0.0001

Data Index: 531157 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 4.0114. Min Range: -4.0114

Max Act: 3.1619. Min Act: -0.0001

Data Index: 179519 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 4.0114. Min Range: -4.0114

Max Act: 3.1172. Min Act: -0.0001

Data Index: 179441 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 4.0114. Min Range: -4.0114

Max Act: 3.0544. Min Act: -0.0001

Data Index: 592267 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 4.0114. Min Range: -4.0114

Max Act: 2.7839. Min Act: -0.0001

Data Index: 1247798 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 4.0114. Min Range: -4.0114

Max Act: 3.0294. Min Act: -0.0001

Data Index: 664513 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 4.0114. Min Range: -4.0114

Max Act: 2.8976. Min Act: -0.0001

Data Index: 834326 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 4.0114. Min Range: -4.0114

Max Act: 2.8020. Min Act: -0.0001

Data Index: 1098971 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 4.0114. Min Range: -4.0114

Max Act: 2.7845. Min Act: -0.0001

Data Index: 306309 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 4.0114. Min Range: -4.0114

Max Act: 2.6327. Min Act: -0.0001

Data Index: 119038 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 4.0114. Min Range: -4.0114

Max Act: 2.4870. Min Act: -0.0001

Data Index: 667508 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 4.0114. Min Range: -4.0114

Max Act: 2.2970. Min Act: -0.0001

Data Index: 627515 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 4.0114. Min Range: -4.0114

Max Act: 2.4257. Min Act: -0.0001

Data Index: 495166 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 4.0114. Min Range: -4.0114

Max Act: 2.2770. Min Act: -0.0000

Data Index: 219153 (C4 (Web Text))

Max Activating Token Index: 924