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

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

Neuron 1675 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.4445. Min Act: -0.0000

Data Index: 97565 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.4219. Min Act: -0.0000

Data Index: 333804 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.2739. Min Act: -0.0000

Data Index: 1339996 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.1775. Min Act: -0.0000

Data Index: 1168709 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.1454. Min Act: -0.0000

Data Index: 160632 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.1344. Min Act: -0.0000

Data Index: 912725 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 1.4445. Min Range: -1.4445

Max Act: 0.9346. Min Act: -0.0000

Data Index: 634733 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 1.4445. Min Range: -1.4445

Max Act: 1.0197. Min Act: -0.0000

Data Index: 350920 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 1.4445. Min Range: -1.4445

Max Act: 0.9405. Min Act: -0.0000

Data Index: 708393 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 1.4445. Min Range: -1.4445

Max Act: 0.9680. Min Act: -0.0000

Data Index: 928588 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 1.4445. Min Range: -1.4445

Max Act: 0.9319. Min Act: -0.0000

Data Index: 945533 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 1.4445. Min Range: -1.4445

Max Act: 0.9440. Min Act: -0.0000

Data Index: 135332 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 1.4445. Min Range: -1.4445

Max Act: 0.9078. Min Act: -0.0000

Data Index: 687603 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 1.4445. Min Range: -1.4445

Max Act: 0.9404. Min Act: -0.0000

Data Index: 988608 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 1.4445. Min Range: -1.4445

Max Act: 0.9403. Min Act: -0.0000

Data Index: 796203 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 1.4445. Min Range: -1.4445

Max Act: 0.8377. Min Act: -0.0000

Data Index: 467132 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 1.4445. Min Range: -1.4445

Max Act: 0.9509. Min Act: -0.0000

Data Index: 451822 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 1.4445. Min Range: -1.4445

Max Act: 0.8796. Min Act: -0.0000

Data Index: 597368 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 1.4445. Min Range: -1.4445

Max Act: 0.9369. Min Act: -0.0000

Data Index: 808097 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 1.4445. Min Range: -1.4445

Max Act: 0.9373. Min Act: -0.0000

Data Index: 1161004 (C4 (Web Text))

Max Activating Token Index: 493