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

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

Neuron 1441 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.4336. Min Act: -0.0000

Data Index: 903548 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.4582. Min Act: -0.0000

Data Index: 234697 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.4656. Min Act: -0.0000

Data Index: 1267005 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.4351. Min Act: -0.0000

Data Index: 173200 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.4189. Min Act: -0.0000

Data Index: 544550 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.4069. Min Act: -0.0000

Data Index: 537494 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3967. Min Act: -0.0000

Data Index: 919993 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.4033. Min Act: -0.0000

Data Index: 439918 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3606. Min Act: -0.0000

Data Index: 587940 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3745. Min Act: -0.0000

Data Index: 323524 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3688. Min Act: -0.0000

Data Index: 107481 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3477. Min Act: -0.0000

Data Index: 276648 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3610. Min Act: -0.0000

Data Index: 1261659 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3011. Min Act: -0.0000

Data Index: 684618 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3514. Min Act: -0.0000

Data Index: 1299658 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3597. Min Act: -0.0000

Data Index: 793992 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3492. Min Act: -0.0000

Data Index: 196783 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1287267 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3369. Min Act: -0.0000

Data Index: 232124 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.4656. Min Range: -0.4656

Max Act: 0.3421. Min Act: -0.0000

Data Index: 276062 (C4 (Web Text))

Max Activating Token Index: 797