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

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

Neuron 158 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1532. Min Range: -3.1532

Max Act: 3.1532. Min Act: -0.0000

Data Index: 1051402 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 3.1532. Min Range: -3.1532

Max Act: 2.9580. Min Act: -0.0000

Data Index: 65894 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 3.1532. Min Range: -3.1532

Max Act: 2.7912. Min Act: -0.0000

Data Index: 736582 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 3.1532. Min Range: -3.1532

Max Act: 2.7463. Min Act: -0.0000

Data Index: 1498221 (Python Code)

Max Activating Token Index: 794

Text #4

Max Range: 3.1532. Min Range: -3.1532

Max Act: 2.4806. Min Act: -0.0000

Data Index: 380472 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 3.1532. Min Range: -3.1532

Max Act: 2.2697. Min Act: -0.0000

Data Index: 1299554 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 3.1532. Min Range: -3.1532

Max Act: 2.3835. Min Act: -0.0000

Data Index: 97317 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 3.1532. Min Range: -3.1532

Max Act: 2.2538. Min Act: -0.0000

Data Index: 652173 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 3.1532. Min Range: -3.1532

Max Act: 2.3136. Min Act: 0.0000

Data Index: 234798 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 3.1532. Min Range: -3.1532

Max Act: 2.0532. Min Act: -0.0000

Data Index: 153086 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 3.1532. Min Range: -3.1532

Max Act: 2.1230. Min Act: -0.0000

Data Index: 926059 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 3.1532. Min Range: -3.1532

Max Act: 2.0752. Min Act: -0.0000

Data Index: 851580 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 3.1532. Min Range: -3.1532

Max Act: 2.0615. Min Act: -0.0000

Data Index: 844988 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 3.1532. Min Range: -3.1532

Max Act: 2.0290. Min Act: -0.0000

Data Index: 165377 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 3.1532. Min Range: -3.1532

Max Act: 2.0202. Min Act: -0.0000

Data Index: 898408 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 3.1532. Min Range: -3.1532

Max Act: 1.9887. Min Act: 0.0000

Data Index: 804793 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 3.1532. Min Range: -3.1532

Max Act: 1.9767. Min Act: -0.0000

Data Index: 63211 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 3.1532. Min Range: -3.1532

Max Act: 1.9632. Min Act: -0.0000

Data Index: 736388 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 3.1532. Min Range: -3.1532

Max Act: 1.8627. Min Act: -0.0000

Data Index: 297801 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 3.1532. Min Range: -3.1532

Max Act: 1.9642. Min Act: -0.0000

Data Index: 603897 (C4 (Web Text))

Max Activating Token Index: 85