Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 356 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.4651. Min Act: -0.0000

Data Index: 779800 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.4259. Min Act: -0.0000

Data Index: 754813 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3098. Min Act: -0.0000

Data Index: 247571 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3216. Min Act: -0.0000

Data Index: 266183 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.3350. Min Act: -0.0000

Data Index: 148103 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.2150. Min Act: -0.0000

Data Index: 611773 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.1877. Min Act: -0.0000

Data Index: 546310 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.2504. Min Act: -0.0000

Data Index: 737035 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.2604. Min Act: -0.0000

Data Index: 550848 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.2527. Min Act: -0.0000

Data Index: 826809 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.1663. Min Act: -0.0000

Data Index: 1120215 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.1388. Min Act: -0.0000

Data Index: 679056 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.1857. Min Act: -0.0000

Data Index: 7754 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.1761. Min Act: -0.0000

Data Index: 865314 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 1.4651. Min Range: -1.4651

Max Act: 0.9518. Min Act: -0.0000

Data Index: 380430 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.1282. Min Act: -0.0000

Data Index: 1216303 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.0302. Min Act: -0.0000

Data Index: 911688 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.0104. Min Act: -0.0000

Data Index: 176505 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 1.4651. Min Range: -1.4651

Max Act: 1.0268. Min Act: -0.0000

Data Index: 1322785 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 1.4651. Min Range: -1.4651

Max Act: 0.9443. Min Act: -0.0000

Data Index: 459213 (C4 (Web Text))

Max Activating Token Index: 353