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

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

Neuron 2840 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1586. Min Range: -4.1586

Max Act: 4.1586. Min Act: -0.0000

Data Index: 1057916 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.8200. Min Act: -0.0000

Data Index: 75720 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.7788. Min Act: -0.0000

Data Index: 1301435 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.7700. Min Act: -0.0000

Data Index: 283297 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.6744. Min Act: -0.0000

Data Index: 64101 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.6282. Min Act: -0.0000

Data Index: 773363 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.4420. Min Act: -0.0000

Data Index: 848412 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.5881. Min Act: -0.0000

Data Index: 761927 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.2206. Min Act: -0.0000

Data Index: 259444 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.5058. Min Act: -0.0000

Data Index: 308140 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.4835. Min Act: -0.0000

Data Index: 247753 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.4735. Min Act: -0.0000

Data Index: 300174 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.4750. Min Act: -0.0000

Data Index: 1416784 (Python Code)

Max Activating Token Index: 550

Text #13

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.2872. Min Act: -0.0000

Data Index: 415526 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.2689. Min Act: -0.0000

Data Index: 588134 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.2613. Min Act: -0.0000

Data Index: 517146 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.4022. Min Act: -0.0000

Data Index: 678215 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.3768. Min Act: -0.0000

Data Index: 271755 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.3868. Min Act: -0.0000

Data Index: 55930 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.3701. Min Act: -0.0000

Data Index: 358496 (C4 (Web Text))

Max Activating Token Index: 114