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

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

Neuron 3497 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: 0.5344. Min Range: -0.5344

Max Act: 0.5327. Min Act: -0.0000

Data Index: 1115865 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.5344. Min Act: -0.0000

Data Index: 186394 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4503. Min Act: -0.0000

Data Index: 457048 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4411. Min Act: -0.0000

Data Index: 337699 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4332. Min Act: -0.0000

Data Index: 431145 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4147. Min Act: -0.0000

Data Index: 390314 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4120. Min Act: 0.0000

Data Index: 243205 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4003. Min Act: -0.0000

Data Index: 813770 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4061. Min Act: -0.0000

Data Index: 529830 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3948. Min Act: -0.0000

Data Index: 840717 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3828. Min Act: -0.0000

Data Index: 305885 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3861. Min Act: -0.0000

Data Index: 1344582 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1195616 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3500. Min Act: -0.0000

Data Index: 737031 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3502. Min Act: -0.0000

Data Index: 585549 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3261. Min Act: -0.0000

Data Index: 432942 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3453. Min Act: -0.0000

Data Index: 450854 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3589. Min Act: -0.0000

Data Index: 1063317 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3449. Min Act: -0.0000

Data Index: 205474 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3350. Min Act: -0.0000

Data Index: 1181582 (C4 (Web Text))

Max Activating Token Index: 698