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

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

Neuron 2173 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: 3.0172. Min Range: -3.0172

Max Act: 3.0172. Min Act: -0.0000

Data Index: 985642 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 3.0172. Min Range: -3.0172

Max Act: 2.5844. Min Act: -0.0000

Data Index: 321950 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 3.0172. Min Range: -3.0172

Max Act: 2.4506. Min Act: -0.0000

Data Index: 1012388 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 3.0172. Min Range: -3.0172

Max Act: 2.4744. Min Act: -0.0000

Data Index: 567868 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 3.0172. Min Range: -3.0172

Max Act: 2.0864. Min Act: -0.0000

Data Index: 1168036 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 3.0172. Min Range: -3.0172

Max Act: 2.4203. Min Act: -0.0000

Data Index: 533354 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 3.0172. Min Range: -3.0172

Max Act: 2.4652. Min Act: -0.0000

Data Index: 1016704 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 3.0172. Min Range: -3.0172

Max Act: 2.2584. Min Act: -0.0000

Data Index: 657087 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 3.0172. Min Range: -3.0172

Max Act: 2.2337. Min Act: -0.0000

Data Index: 1589663 (Python Code)

Max Activating Token Index: 577

Text #9

Max Range: 3.0172. Min Range: -3.0172

Max Act: 2.4669. Min Act: -0.0000

Data Index: 599245 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 3.0172. Min Range: -3.0172

Max Act: 2.1781. Min Act: -0.0000

Data Index: 1202731 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 3.0172. Min Range: -3.0172

Max Act: 2.3131. Min Act: -0.0000

Data Index: 271787 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 3.0172. Min Range: -3.0172

Max Act: 2.1605. Min Act: -0.0000

Data Index: 997467 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 3.0172. Min Range: -3.0172

Max Act: 2.1239. Min Act: -0.0000

Data Index: 899706 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 3.0172. Min Range: -3.0172

Max Act: 2.2656. Min Act: -0.0000

Data Index: 749299 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 3.0172. Min Range: -3.0172

Max Act: 1.7450. Min Act: -0.0000

Data Index: 197060 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 3.0172. Min Range: -3.0172

Max Act: 2.3259. Min Act: -0.0000

Data Index: 566593 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 3.0172. Min Range: -3.0172

Max Act: 2.1898. Min Act: -0.0000

Data Index: 969974 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 3.0172. Min Range: -3.0172

Max Act: 2.1366. Min Act: -0.0000

Data Index: 1328171 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 3.0172. Min Range: -3.0172

Max Act: 2.0164. Min Act: -0.0000

Data Index: 431084 (C4 (Web Text))

Max Activating Token Index: 602