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

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

Neuron 5823 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.4591. Min Act: -0.0001

Data Index: 127900 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.3394. Min Act: -0.0001

Data Index: 576643 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.2067. Min Act: -0.0001

Data Index: 795124 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.0991. Min Act: -0.0001

Data Index: 517044 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.0321. Min Act: -0.0001

Data Index: 109017 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.0238. Min Act: -0.0001

Data Index: 63875 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.0497. Min Act: -0.0001

Data Index: 726605 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.1070. Min Act: -0.0001

Data Index: 1343117 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.1518. Min Act: -0.0001

Data Index: 160964 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.0401. Min Act: -0.0001

Data Index: 774934 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.9995. Min Act: -0.0001

Data Index: 874875 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.8630. Min Act: -0.0001

Data Index: 941318 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.0389. Min Act: -0.0001

Data Index: 1116462 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.9834. Min Act: -0.0001

Data Index: 14771 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.0255. Min Act: -0.0001

Data Index: 633675 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.0374. Min Act: -0.0001

Data Index: 212937 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.8965. Min Act: -0.0001

Data Index: 563344 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 1.4591. Min Range: -1.4591

Max Act: 1.0258. Min Act: -0.0001

Data Index: 743569 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.8706. Min Act: -0.0001

Data Index: 92342 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 1.4591. Min Range: -1.4591

Max Act: 0.9076. Min Act: -0.0001

Data Index: 1092505 (C4 (Web Text))

Max Activating Token Index: 726