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

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

Neuron 2987 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: 0.4640. Min Range: -0.4640

Max Act: 0.4640. Min Act: -0.0000

Data Index: 570331 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1114665 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3752. Min Act: -0.0000

Data Index: 321564 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3923. Min Act: -0.0000

Data Index: 1351905 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3556. Min Act: -0.0000

Data Index: 437760 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3359. Min Act: -0.0000

Data Index: 149078 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3157. Min Act: -0.0000

Data Index: 20968 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3627. Min Act: -0.0000

Data Index: 245504 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3503. Min Act: -0.0000

Data Index: 1035944 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3360. Min Act: -0.0000

Data Index: 989271 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3416. Min Act: -0.0000

Data Index: 692393 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3601. Min Act: -0.0000

Data Index: 139084 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3564. Min Act: -0.0000

Data Index: 355323 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3359. Min Act: -0.0000

Data Index: 108393 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3444. Min Act: -0.0000

Data Index: 1181555 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3436. Min Act: -0.0000

Data Index: 875904 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3211. Min Act: -0.0000

Data Index: 350900 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3567. Min Act: -0.0000

Data Index: 1176398 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3081. Min Act: -0.0000

Data Index: 1261279 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3639. Min Act: -0.0000

Data Index: 866249 (C4 (Web Text))

Max Activating Token Index: 287