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

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

Neuron 3746 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.2354. Min Act: -0.0000

Data Index: 1207065 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.3794. Min Act: -0.0000

Data Index: 606564 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.0785. Min Act: -0.0000

Data Index: 12174 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.6745. Min Act: -0.0000

Data Index: 988492 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.9212. Min Act: -0.0001

Data Index: 276056 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.7376. Min Act: -0.0001

Data Index: 330194 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.4651. Min Act: -0.0001

Data Index: 1335710 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.3588. Min Act: -0.0000

Data Index: 973112 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.2745. Min Act: -0.0001

Data Index: 538756 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.3743. Min Act: -0.0001

Data Index: 94710 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.1540. Min Act: -0.0001

Data Index: 511627 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.2164. Min Act: -0.0001

Data Index: 658644 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.1877. Min Act: -0.0000

Data Index: 1267451 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.1653. Min Act: -0.0001

Data Index: 545037 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.0471. Min Act: -0.0000

Data Index: 45578 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.0117. Min Act: -0.0001

Data Index: 570692 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.1051. Min Act: -0.0000

Data Index: 1137340 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.0504. Min Act: -0.0001

Data Index: 621306 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 3.3794. Min Range: -3.3794

Max Act: 1.9359. Min Act: -0.0000

Data Index: 360148 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.2569. Min Act: -0.0000

Data Index: 49818 (C4 (Web Text))

Max Activating Token Index: 686