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

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

Neuron 760 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6698. Min Range: -2.6698

Max Act: 2.6698. Min Act: -0.0000

Data Index: 171436 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 2.6698. Min Range: -2.6698

Max Act: 2.6195. Min Act: -0.0000

Data Index: 940454 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 2.6698. Min Range: -2.6698

Max Act: 2.4006. Min Act: -0.0000

Data Index: 169355 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 2.6698. Min Range: -2.6698

Max Act: 2.5653. Min Act: -0.0000

Data Index: 393564 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 2.6698. Min Range: -2.6698

Max Act: 2.5196. Min Act: -0.0000

Data Index: 1045485 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 2.6698. Min Range: -2.6698

Max Act: 2.3338. Min Act: -0.0000

Data Index: 1012537 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 2.6698. Min Range: -2.6698

Max Act: 2.4795. Min Act: -0.0000

Data Index: 1003558 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 2.6698. Min Range: -2.6698

Max Act: 2.4350. Min Act: -0.0000

Data Index: 1075416 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 2.6698. Min Range: -2.6698

Max Act: 2.4144. Min Act: -0.0000

Data Index: 756244 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 2.6698. Min Range: -2.6698

Max Act: 2.3826. Min Act: -0.0000

Data Index: 797436 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 2.6698. Min Range: -2.6698

Max Act: 2.3686. Min Act: -0.0000

Data Index: 1176527 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 2.6698. Min Range: -2.6698

Max Act: 2.4926. Min Act: -0.0000

Data Index: 651592 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 2.6698. Min Range: -2.6698

Max Act: 2.4714. Min Act: -0.0000

Data Index: 1093681 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 2.6698. Min Range: -2.6698

Max Act: 2.3392. Min Act: -0.0000

Data Index: 367146 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 2.6698. Min Range: -2.6698

Max Act: 2.4070. Min Act: -0.0000

Data Index: 811825 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 2.6698. Min Range: -2.6698

Max Act: 2.2963. Min Act: -0.0000

Data Index: 204395 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 2.6698. Min Range: -2.6698

Max Act: 2.2615. Min Act: -0.0000

Data Index: 1084279 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 2.6698. Min Range: -2.6698

Max Act: 2.2695. Min Act: -0.0000

Data Index: 347936 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 2.6698. Min Range: -2.6698

Max Act: 2.2487. Min Act: -0.0000

Data Index: 311032 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 2.6698. Min Range: -2.6698

Max Act: 2.2397. Min Act: -0.0000

Data Index: 1266361 (C4 (Web Text))

Max Activating Token Index: 227