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

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

Neuron 150 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: 0.5075. Min Range: -0.5075

Max Act: 0.5075. Min Act: -0.0000

Data Index: 1163754 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4470. Min Act: -0.0000

Data Index: 342643 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4373. Min Act: -0.0000

Data Index: 269865 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4329. Min Act: -0.0000

Data Index: 1009607 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1023156 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4114. Min Act: -0.0000

Data Index: 475204 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4053. Min Act: -0.0001

Data Index: 85971 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3913. Min Act: -0.0001

Data Index: 161072 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4040. Min Act: -0.0000

Data Index: 1213788 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3926. Min Act: -0.0001

Data Index: 435700 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1068842 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3748. Min Act: -0.0000

Data Index: 949301 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3474. Min Act: -0.0001

Data Index: 84197 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3470. Min Act: -0.0000

Data Index: 1198641 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3428. Min Act: -0.0000

Data Index: 893129 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3557. Min Act: -0.0000

Data Index: 487602 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3550. Min Act: -0.0000

Data Index: 125525 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3666. Min Act: -0.0000

Data Index: 507972 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3471. Min Act: -0.0000

Data Index: 649383 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3315. Min Act: -0.0000

Data Index: 948449 (C4 (Web Text))

Max Activating Token Index: 252