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

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

Neuron 5325 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.9466. Min Act: -0.0000

Data Index: 599743 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.4701. Min Act: -0.0000

Data Index: 1265647 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.3793. Min Act: -0.0000

Data Index: 398868 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.3323. Min Act: -0.0000

Data Index: 1114250 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.2895. Min Act: -0.0000

Data Index: 517249 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.1654. Min Act: -0.0000

Data Index: 386389 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.1929. Min Act: -0.0000

Data Index: 872782 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.0087. Min Act: -0.0000

Data Index: 448598 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.1537. Min Act: -0.0000

Data Index: 385151 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.1463. Min Act: -0.0000

Data Index: 641939 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 1.9466. Min Range: -1.9466

Max Act: 0.9922. Min Act: -0.0000

Data Index: 1254733 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.0599. Min Act: -0.0000

Data Index: 602635 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.0172. Min Act: -0.0000

Data Index: 375495 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 1.9466. Min Range: -1.9466

Max Act: 1.0287. Min Act: -0.0000

Data Index: 1177107 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 1.9466. Min Range: -1.9466

Max Act: 0.9678. Min Act: -0.0000

Data Index: 882848 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 1.9466. Min Range: -1.9466

Max Act: 0.9917. Min Act: -0.0000

Data Index: 431274 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 1.9466. Min Range: -1.9466

Max Act: 0.9764. Min Act: -0.0000

Data Index: 184484 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 1.9466. Min Range: -1.9466

Max Act: 0.9437. Min Act: -0.0000

Data Index: 1026576 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 1.9466. Min Range: -1.9466

Max Act: 0.9765. Min Act: -0.0000

Data Index: 581305 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 1.9466. Min Range: -1.9466

Max Act: 0.9599. Min Act: -0.0000

Data Index: 686744 (C4 (Web Text))

Max Activating Token Index: 833