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

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

Neuron 3386 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8442. Min Range: -4.8442

Max Act: 4.8442. Min Act: -0.0000

Data Index: 417193 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 4.8442. Min Range: -4.8442

Max Act: 4.5549. Min Act: -0.0000

Data Index: 104278 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 4.8442. Min Range: -4.8442

Max Act: 3.9992. Min Act: -0.0000

Data Index: 749274 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 4.8442. Min Range: -4.8442

Max Act: 3.8692. Min Act: -0.0000

Data Index: 57599 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 4.8442. Min Range: -4.8442

Max Act: 3.7258. Min Act: -0.0000

Data Index: 708724 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 4.8442. Min Range: -4.8442

Max Act: 3.8390. Min Act: -0.0000

Data Index: 450584 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 4.8442. Min Range: -4.8442

Max Act: 3.6505. Min Act: -0.0000

Data Index: 511508 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 4.8442. Min Range: -4.8442

Max Act: 3.4625. Min Act: -0.0000

Data Index: 741565 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 4.8442. Min Range: -4.8442

Max Act: 3.1867. Min Act: -0.0000

Data Index: 910919 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 4.8442. Min Range: -4.8442

Max Act: 3.2397. Min Act: -0.0000

Data Index: 1285084 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 4.8442. Min Range: -4.8442

Max Act: 3.3843. Min Act: -0.0000

Data Index: 737381 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 4.8442. Min Range: -4.8442

Max Act: 3.3714. Min Act: -0.0000

Data Index: 846290 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 4.8442. Min Range: -4.8442

Max Act: 3.5174. Min Act: -0.0000

Data Index: 251783 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 4.8442. Min Range: -4.8442

Max Act: 3.2977. Min Act: -0.0000

Data Index: 90513 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 4.8442. Min Range: -4.8442

Max Act: 3.2997. Min Act: -0.0000

Data Index: 1181154 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 4.8442. Min Range: -4.8442

Max Act: 3.2684. Min Act: -0.0000

Data Index: 337188 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 4.8442. Min Range: -4.8442

Max Act: 3.4241. Min Act: -0.0000

Data Index: 1112167 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 4.8442. Min Range: -4.8442

Max Act: 3.2539. Min Act: 0.0000

Data Index: 634623 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 4.8442. Min Range: -4.8442

Max Act: 3.0565. Min Act: -0.0000

Data Index: 254653 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 4.8442. Min Range: -4.8442

Max Act: 3.1833. Min Act: -0.0000

Data Index: 124868 (C4 (Web Text))

Max Activating Token Index: 398