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

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

Neuron 3596 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2278. Min Range: -1.2278

Max Act: 1.2278. Min Act: -0.0000

Data Index: 1241518 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9853. Min Act: -0.0000

Data Index: 1088097 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9917. Min Act: 0.0000

Data Index: 761924 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9953. Min Act: -0.0001

Data Index: 451805 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9622. Min Act: 0.0001

Data Index: 1021366 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9596. Min Act: 0.0001

Data Index: 52220 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9612. Min Act: -0.0000

Data Index: 107645 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.8962. Min Act: 0.0001

Data Index: 718353 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9489. Min Act: 0.0000

Data Index: 833829 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9081. Min Act: 0.0000

Data Index: 70506 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.8998. Min Act: -0.0000

Data Index: 1140381 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.8743. Min Act: 0.0000

Data Index: 1197588 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.8754. Min Act: 0.0001

Data Index: 604306 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.8599. Min Act: -0.0001

Data Index: 350645 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.8471. Min Act: 0.0000

Data Index: 1065782 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.8705. Min Act: 0.0001

Data Index: 567998 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.8306. Min Act: -0.0000

Data Index: 637624 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.8060. Min Act: -0.0000

Data Index: 26411 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.8275. Min Act: 0.0001

Data Index: 321700 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.8530. Min Act: 0.0001

Data Index: 328735 (C4 (Web Text))

Max Activating Token Index: 604