Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3277 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.2138. Min Range: -4.2138

Max Act: 4.2138. Min Act: -0.0000

Data Index: 1485863 (Python Code)

Max Activating Token Index: 199

Text #1

Max Range: 4.2138. Min Range: -4.2138

Max Act: 3.6926. Min Act: -0.0001

Data Index: 1461528 (Python Code)

Max Activating Token Index: 718

Text #2

Max Range: 4.2138. Min Range: -4.2138

Max Act: 3.3651. Min Act: -0.0001

Data Index: 523381 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 4.2138. Min Range: -4.2138

Max Act: 3.3412. Min Act: -0.0001

Data Index: 1601440 (Python Code)

Max Activating Token Index: 151

Text #4

Max Range: 4.2138. Min Range: -4.2138

Max Act: 3.4689. Min Act: -0.0001

Data Index: 1542438 (Python Code)

Max Activating Token Index: 1012

Text #5

Max Range: 4.2138. Min Range: -4.2138

Max Act: 3.3055. Min Act: -0.0001

Data Index: 1657078 (Python Code)

Max Activating Token Index: 399

Text #6

Max Range: 4.2138. Min Range: -4.2138

Max Act: 3.3650. Min Act: -0.0001

Data Index: 1516069 (Python Code)

Max Activating Token Index: 473

Text #7

Max Range: 4.2138. Min Range: -4.2138

Max Act: 2.9928. Min Act: -0.0001

Data Index: 1364338 (Python Code)

Max Activating Token Index: 887

Text #8

Max Range: 4.2138. Min Range: -4.2138

Max Act: 2.9310. Min Act: -0.0000

Data Index: 57720 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 4.2138. Min Range: -4.2138

Max Act: 2.9166. Min Act: -0.0000

Data Index: 354763 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 4.2138. Min Range: -4.2138

Max Act: 2.9339. Min Act: -0.0001

Data Index: 47727 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 4.2138. Min Range: -4.2138

Max Act: 2.7755. Min Act: -0.0001

Data Index: 1507812 (Python Code)

Max Activating Token Index: 502

Text #12

Max Range: 4.2138. Min Range: -4.2138

Max Act: 2.9172. Min Act: -0.0000

Data Index: 1389209 (Python Code)

Max Activating Token Index: 283

Text #13

Max Range: 4.2138. Min Range: -4.2138

Max Act: 2.6221. Min Act: -0.0000

Data Index: 1620315 (Python Code)

Max Activating Token Index: 586

Text #14

Max Range: 4.2138. Min Range: -4.2138

Max Act: 2.7431. Min Act: -0.0000

Data Index: 842539 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 4.2138. Min Range: -4.2138

Max Act: 2.7420. Min Act: -0.0001

Data Index: 1228762 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 4.2138. Min Range: -4.2138

Max Act: 2.7175. Min Act: -0.0000

Data Index: 1432091 (Python Code)

Max Activating Token Index: 42

Text #17

Max Range: 4.2138. Min Range: -4.2138

Max Act: 2.7258. Min Act: -0.0001

Data Index: 1605161 (Python Code)

Max Activating Token Index: 824

Text #18

Max Range: 4.2138. Min Range: -4.2138

Max Act: 2.5381. Min Act: -0.0001

Data Index: 347122 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 4.2138. Min Range: -4.2138

Max Act: 2.7849. Min Act: -0.0000

Data Index: 601856 (C4 (Web Text))

Max Activating Token Index: 311