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

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

Neuron 1553 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: 2.9860. Min Range: -2.9860

Max Act: 2.9439. Min Act: -0.0000

Data Index: 7187 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 2.9860. Min Range: -2.9860

Max Act: 2.9860. Min Act: -0.0000

Data Index: 77843 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 2.9860. Min Range: -2.9860

Max Act: 2.7618. Min Act: -0.0000

Data Index: 885768 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 2.9860. Min Range: -2.9860

Max Act: 2.8933. Min Act: -0.0000

Data Index: 1060309 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 2.9860. Min Range: -2.9860

Max Act: 2.6853. Min Act: -0.0000

Data Index: 334355 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 2.9860. Min Range: -2.9860

Max Act: 2.2475. Min Act: -0.0000

Data Index: 1137428 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 2.9860. Min Range: -2.9860

Max Act: 2.4689. Min Act: -0.0000

Data Index: 882848 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 2.9860. Min Range: -2.9860

Max Act: 2.5685. Min Act: -0.0000

Data Index: 460616 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 2.9860. Min Range: -2.9860

Max Act: 2.2752. Min Act: -0.0000

Data Index: 330382 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 2.9860. Min Range: -2.9860

Max Act: 2.4276. Min Act: 0.0000

Data Index: 289750 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 2.9860. Min Range: -2.9860

Max Act: 2.2280. Min Act: -0.0000

Data Index: 314474 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 2.9860. Min Range: -2.9860

Max Act: 2.1326. Min Act: -0.0000

Data Index: 187836 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 2.9860. Min Range: -2.9860

Max Act: 2.2398. Min Act: -0.0000

Data Index: 526333 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 2.9860. Min Range: -2.9860

Max Act: 2.2554. Min Act: -0.0000

Data Index: 490438 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 2.9860. Min Range: -2.9860

Max Act: 2.1149. Min Act: -0.0000

Data Index: 798656 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 2.9860. Min Range: -2.9860

Max Act: 2.2273. Min Act: -0.0000

Data Index: 235191 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 2.9860. Min Range: -2.9860

Max Act: 2.1748. Min Act: -0.0000

Data Index: 1017116 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 2.9860. Min Range: -2.9860

Max Act: 2.0663. Min Act: -0.0000

Data Index: 861287 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 2.9860. Min Range: -2.9860

Max Act: 1.8396. Min Act: -0.0000

Data Index: 194058 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 2.9860. Min Range: -2.9860

Max Act: 2.1729. Min Act: -0.0000

Data Index: 1140550 (C4 (Web Text))

Max Activating Token Index: 978