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

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

Neuron 3491 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.9920. Min Act: -0.0000

Data Index: 702705 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 1.0334. Min Range: -1.0334

Max Act: 1.0334. Min Act: -0.0000

Data Index: 543990 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.9822. Min Act: -0.0000

Data Index: 266669 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 1.0334. Min Range: -1.0334

Max Act: 1.0082. Min Act: -0.0000

Data Index: 1344307 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.9755. Min Act: -0.0000

Data Index: 615866 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.9180. Min Act: -0.0000

Data Index: 517699 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.9495. Min Act: -0.0000

Data Index: 531241 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.9356. Min Act: -0.0000

Data Index: 594474 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.9218. Min Act: 0.0000

Data Index: 772766 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.9045. Min Act: 0.0000

Data Index: 1095940 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8791. Min Act: -0.0000

Data Index: 589028 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8751. Min Act: -0.0000

Data Index: 84342 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8409. Min Act: -0.0000

Data Index: 520849 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8432. Min Act: -0.0000

Data Index: 467603 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8046. Min Act: -0.0000

Data Index: 665863 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8084. Min Act: -0.0000

Data Index: 305578 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8205. Min Act: -0.0000

Data Index: 830070 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8450. Min Act: -0.0000

Data Index: 966562 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.7890. Min Act: -0.0000

Data Index: 909059 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.7827. Min Act: -0.0000

Data Index: 1357402 (C4 (Web Text))

Max Activating Token Index: 992