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

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

Neuron 3367 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: 0.5912. Min Range: -0.5912

Max Act: 0.5912. Min Act: -0.0000

Data Index: 159031 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.5236. Min Act: -0.0001

Data Index: 359845 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4859. Min Act: -0.0001

Data Index: 79256 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4971. Min Act: -0.0000

Data Index: 1294979 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1236908 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4914. Min Act: -0.0001

Data Index: 826482 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4547. Min Act: -0.0000

Data Index: 34038 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4640. Min Act: -0.0001

Data Index: 952491 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4347. Min Act: -0.0000

Data Index: 230619 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4478. Min Act: -0.0000

Data Index: 643126 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4342. Min Act: -0.0000

Data Index: 160304 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4438. Min Act: -0.0000

Data Index: 822023 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4372. Min Act: -0.0000

Data Index: 1081383 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4343. Min Act: -0.0000

Data Index: 509581 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4365. Min Act: -0.0000

Data Index: 222347 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4371. Min Act: -0.0000

Data Index: 951314 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4213. Min Act: -0.0000

Data Index: 568036 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4343. Min Act: -0.0001

Data Index: 954862 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4439. Min Act: -0.0000

Data Index: 686488 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4051. Min Act: -0.0000

Data Index: 1208145 (C4 (Web Text))

Max Activating Token Index: 265