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

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

Neuron 1964 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.3445. Min Act: -0.0001

Data Index: 685598 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.3178. Min Act: -0.0000

Data Index: 849303 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.3461. Min Act: -0.0001

Data Index: 542472 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.3313. Min Act: -0.0001

Data Index: 612692 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.3105. Min Act: -0.0001

Data Index: 340525 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2918. Min Act: -0.0001

Data Index: 189388 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2681. Min Act: -0.0001

Data Index: 385634 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.3043. Min Act: -0.0001

Data Index: 171622 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2821. Min Act: -0.0001

Data Index: 595298 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2838. Min Act: -0.0001

Data Index: 360550 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2791. Min Act: -0.0001

Data Index: 762745 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2818. Min Act: -0.0001

Data Index: 184882 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2722. Min Act: -0.0001

Data Index: 472208 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2826. Min Act: -0.0001

Data Index: 442449 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2652. Min Act: -0.0001

Data Index: 586311 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2654. Min Act: -0.0001

Data Index: 466889 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2500. Min Act: -0.0001

Data Index: 848268 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2579. Min Act: -0.0001

Data Index: 1470232 (Python Code)

Max Activating Token Index: 381

Text #18

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2653. Min Act: -0.0001

Data Index: 384546 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2833. Min Act: -0.0001

Data Index: 706147 (C4 (Web Text))

Max Activating Token Index: 795