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

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

Neuron 1291 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: 1.3862. Min Range: -1.3862

Max Act: 1.3862. Min Act: -0.0000

Data Index: 1645589 (Python Code)

Max Activating Token Index: 714

Text #1

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.1503. Min Act: -0.0000

Data Index: 1580091 (Python Code)

Max Activating Token Index: 1010

Text #2

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.0661. Min Act: -0.0000

Data Index: 1522524 (Python Code)

Max Activating Token Index: 324

Text #3

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.0343. Min Act: -0.0000

Data Index: 1638295 (Python Code)

Max Activating Token Index: 284

Text #4

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.9562. Min Act: -0.0000

Data Index: 998735 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.9774. Min Act: -0.0000

Data Index: 1482638 (Python Code)

Max Activating Token Index: 371

Text #6

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.9632. Min Act: 0.0000

Data Index: 638418 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.9413. Min Act: -0.0000

Data Index: 139772 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.8978. Min Act: -0.0000

Data Index: 311264 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.9049. Min Act: -0.0000

Data Index: 507730 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.8789. Min Act: -0.0000

Data Index: 1358075 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.8406. Min Act: -0.0000

Data Index: 710096 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.8641. Min Act: -0.0000

Data Index: 384890 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.8604. Min Act: -0.0000

Data Index: 1498700 (Python Code)

Max Activating Token Index: 52

Text #14

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.8407. Min Act: -0.0000

Data Index: 844276 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.7998. Min Act: -0.0000

Data Index: 1165001 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.8147. Min Act: -0.0000

Data Index: 335759 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.7652. Min Act: -0.0000

Data Index: 1281842 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.8127. Min Act: -0.0000

Data Index: 411692 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.7677. Min Act: -0.0000

Data Index: 1112573 (C4 (Web Text))

Max Activating Token Index: 998