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

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

Neuron 2683 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: 1.2862. Min Range: -1.2862

Max Act: 1.2862. Min Act: -0.0000

Data Index: 1122582 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 1.2862. Min Range: -1.2862

Max Act: 1.1905. Min Act: -0.0000

Data Index: 318221 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 1.2862. Min Range: -1.2862

Max Act: 1.0890. Min Act: -0.0000

Data Index: 366071 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 1.2862. Min Range: -1.2862

Max Act: 1.0911. Min Act: -0.0000

Data Index: 409230 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 1.2862. Min Range: -1.2862

Max Act: 1.0645. Min Act: -0.0000

Data Index: 1268861 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 1.2862. Min Range: -1.2862

Max Act: 1.0383. Min Act: -0.0000

Data Index: 442844 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 1.2862. Min Range: -1.2862

Max Act: 1.0048. Min Act: -0.0000

Data Index: 243088 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 1.2862. Min Range: -1.2862

Max Act: 0.9678. Min Act: -0.0000

Data Index: 60996 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 1.2862. Min Range: -1.2862

Max Act: 0.9685. Min Act: -0.0000

Data Index: 20598 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 1.2862. Min Range: -1.2862

Max Act: 0.9120. Min Act: -0.0000

Data Index: 1215352 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 1.2862. Min Range: -1.2862

Max Act: 0.9646. Min Act: -0.0000

Data Index: 436592 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 1.2862. Min Range: -1.2862

Max Act: 0.9192. Min Act: -0.0000

Data Index: 112184 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 1.2862. Min Range: -1.2862

Max Act: 0.9424. Min Act: -0.0000

Data Index: 809516 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 1.2862. Min Range: -1.2862

Max Act: 0.9480. Min Act: -0.0000

Data Index: 819215 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 1.2862. Min Range: -1.2862

Max Act: 0.9419. Min Act: -0.0000

Data Index: 698770 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 1.2862. Min Range: -1.2862

Max Act: 0.9542. Min Act: -0.0000

Data Index: 181224 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 1.2862. Min Range: -1.2862

Max Act: 0.9018. Min Act: -0.0000

Data Index: 432358 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 1.2862. Min Range: -1.2862

Max Act: 0.9025. Min Act: -0.0000

Data Index: 455863 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 1.2862. Min Range: -1.2862

Max Act: 0.9474. Min Act: -0.0000

Data Index: 848869 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 1.2862. Min Range: -1.2862

Max Act: 0.9482. Min Act: -0.0000

Data Index: 1156889 (C4 (Web Text))

Max Activating Token Index: 356