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

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

Neuron 5056 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6256. Min Range: -0.6256

Max Act: 0.6256. Min Act: -0.0001

Data Index: 821728 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 0.6256. Min Range: -0.6256

Max Act: 0.5849. Min Act: -0.0000

Data Index: 1083236 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 0.6256. Min Range: -0.6256

Max Act: 0.5478. Min Act: -0.0001

Data Index: 610946 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.6256. Min Range: -0.6256

Max Act: 0.5639. Min Act: -0.0001

Data Index: 1229519 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.6256. Min Range: -0.6256

Max Act: 0.5214. Min Act: -0.0000

Data Index: 1163324 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 0.6256. Min Range: -0.6256

Max Act: 0.4716. Min Act: -0.0001

Data Index: 1115823 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.6256. Min Range: -0.6256

Max Act: 0.5049. Min Act: -0.0001

Data Index: 382239 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.6256. Min Range: -0.6256

Max Act: 0.5000. Min Act: -0.0001

Data Index: 218804 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.6256. Min Range: -0.6256

Max Act: 0.4819. Min Act: -0.0001

Data Index: 989765 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.6256. Min Range: -0.6256

Max Act: 0.4684. Min Act: -0.0001

Data Index: 969117 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 0.6256. Min Range: -0.6256

Max Act: 0.4664. Min Act: -0.0001

Data Index: 1138916 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.6256. Min Range: -0.6256

Max Act: 0.4600. Min Act: -0.0001

Data Index: 158954 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 0.6256. Min Range: -0.6256

Max Act: 0.4419. Min Act: -0.0000

Data Index: 623342 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 0.6256. Min Range: -0.6256

Max Act: 0.4577. Min Act: -0.0001

Data Index: 135149 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.6256. Min Range: -0.6256

Max Act: 0.4499. Min Act: -0.0001

Data Index: 1013546 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.6256. Min Range: -0.6256

Max Act: 0.4496. Min Act: -0.0001

Data Index: 476436 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.6256. Min Range: -0.6256

Max Act: 0.4211. Min Act: -0.0001

Data Index: 79468 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.6256. Min Range: -0.6256

Max Act: 0.4325. Min Act: -0.0001

Data Index: 1146864 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.6256. Min Range: -0.6256

Max Act: 0.4762. Min Act: -0.0001

Data Index: 503755 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.6256. Min Range: -0.6256

Max Act: 0.4608. Min Act: -0.0000

Data Index: 504826 (C4 (Web Text))

Max Activating Token Index: 224