Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3950 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7002. Min Range: -1.7002

Max Act: 1.6532. Min Act: -0.0000

Data Index: 29763 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 1.7002. Min Range: -1.7002

Max Act: 1.7002. Min Act: -0.0000

Data Index: 905422 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 1.7002. Min Range: -1.7002

Max Act: 1.4996. Min Act: -0.0000

Data Index: 991900 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 1.7002. Min Range: -1.7002

Max Act: 1.3030. Min Act: -0.0000

Data Index: 1077991 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 1.7002. Min Range: -1.7002

Max Act: 1.3425. Min Act: -0.0000

Data Index: 526319 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 1.7002. Min Range: -1.7002

Max Act: 1.3418. Min Act: -0.0000

Data Index: 430122 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 1.7002. Min Range: -1.7002

Max Act: 1.2197. Min Act: -0.0000

Data Index: 88354 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 1.7002. Min Range: -1.7002

Max Act: 1.3146. Min Act: -0.0000

Data Index: 484265 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 1.7002. Min Range: -1.7002

Max Act: 1.2927. Min Act: -0.0000

Data Index: 842436 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 1.7002. Min Range: -1.7002

Max Act: 1.2774. Min Act: -0.0000

Data Index: 992637 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 1.7002. Min Range: -1.7002

Max Act: 1.1237. Min Act: -0.0000

Data Index: 384635 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 1.7002. Min Range: -1.7002

Max Act: 1.1743. Min Act: -0.0000

Data Index: 1116493 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 1.7002. Min Range: -1.7002

Max Act: 1.1529. Min Act: -0.0000

Data Index: 1329030 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 1.7002. Min Range: -1.7002

Max Act: 1.0412. Min Act: -0.0000

Data Index: 398451 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 1.7002. Min Range: -1.7002

Max Act: 1.2739. Min Act: -0.0000

Data Index: 54480 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 1.7002. Min Range: -1.7002

Max Act: 1.1385. Min Act: -0.0000

Data Index: 166282 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 1.7002. Min Range: -1.7002

Max Act: 1.0657. Min Act: -0.0000

Data Index: 694360 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 1.7002. Min Range: -1.7002

Max Act: 1.0407. Min Act: -0.0000

Data Index: 249401 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 1.7002. Min Range: -1.7002

Max Act: 1.0967. Min Act: -0.0000

Data Index: 16647 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 1.7002. Min Range: -1.7002

Max Act: 1.0951. Min Act: -0.0000

Data Index: 711639 (C4 (Web Text))

Max Activating Token Index: 1013