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

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

Neuron 671 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.6407. Min Act: -0.0000

Data Index: 974151 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1277654 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.6286. Min Act: -0.0000

Data Index: 310683 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1288568 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.5563. Min Act: -0.0000

Data Index: 388344 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.5511. Min Act: -0.0000

Data Index: 820990 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1011746 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.5163. Min Act: -0.0000

Data Index: 1098849 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.5305. Min Act: -0.0000

Data Index: 88202 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.4884. Min Act: -0.0000

Data Index: 737546 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.5093. Min Act: -0.0000

Data Index: 1162621 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.4890. Min Act: -0.0000

Data Index: 306914 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.5050. Min Act: -0.0000

Data Index: 647467 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.4886. Min Act: -0.0000

Data Index: 474480 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.4595. Min Act: -0.0000

Data Index: 317958 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.4558. Min Act: -0.0000

Data Index: 1302470 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.4683. Min Act: -0.0000

Data Index: 860677 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.4742. Min Act: -0.0000

Data Index: 606844 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.4685. Min Act: -0.0000

Data Index: 230925 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.6407. Min Range: -0.6407

Max Act: 0.4534. Min Act: -0.0000

Data Index: 13668 (C4 (Web Text))

Max Activating Token Index: 396