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

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

Neuron 674 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.7585. Min Act: -0.0001

Data Index: 813507 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6325. Min Act: -0.0001

Data Index: 932685 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6056. Min Act: -0.0001

Data Index: 1128498 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5805. Min Act: -0.0001

Data Index: 492683 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5976. Min Act: -0.0001

Data Index: 678560 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5908. Min Act: -0.0001

Data Index: 846426 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5467. Min Act: -0.0001

Data Index: 1002016 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5763. Min Act: -0.0001

Data Index: 1351189 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5961. Min Act: -0.0001

Data Index: 1268222 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5738. Min Act: -0.0001

Data Index: 721538 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5570. Min Act: -0.0001

Data Index: 46494 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.6010. Min Act: -0.0001

Data Index: 125999 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5617. Min Act: -0.0001

Data Index: 49911 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5610. Min Act: -0.0001

Data Index: 642226 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5692. Min Act: -0.0001

Data Index: 1098918 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5292. Min Act: -0.0001

Data Index: 865049 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5619. Min Act: -0.0000

Data Index: 804017 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5188. Min Act: -0.0001

Data Index: 1347216 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5168. Min Act: -0.0001

Data Index: 572052 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.7585. Min Range: -0.7585

Max Act: 0.5513. Min Act: -0.0001

Data Index: 176918 (C4 (Web Text))

Max Activating Token Index: 500