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

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

Neuron 1008 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7560. Min Range: -0.7560

Max Act: 0.7497. Min Act: -0.0001

Data Index: 698505 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.7560. Min Range: -0.7560

Max Act: 0.7560. Min Act: -0.0001

Data Index: 151852 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.7560. Min Range: -0.7560

Max Act: 0.7494. Min Act: -0.0001

Data Index: 1550416 (Python Code)

Max Activating Token Index: 399

Text #3

Max Range: 0.7560. Min Range: -0.7560

Max Act: 0.7294. Min Act: -0.0001

Data Index: 557140 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.7560. Min Range: -0.7560

Max Act: 0.7266. Min Act: -0.0001

Data Index: 701490 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.7560. Min Range: -0.7560

Max Act: 0.6739. Min Act: -0.0001

Data Index: 448710 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.7560. Min Range: -0.7560

Max Act: 0.6719. Min Act: -0.0001

Data Index: 625147 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.7560. Min Range: -0.7560

Max Act: 0.6554. Min Act: -0.0001

Data Index: 1650664 (Python Code)

Max Activating Token Index: 765

Text #8

Max Range: 0.7560. Min Range: -0.7560

Max Act: 0.6362. Min Act: -0.0001

Data Index: 1645687 (Python Code)

Max Activating Token Index: 767

Text #9

Max Range: 0.7560. Min Range: -0.7560

Max Act: 0.6618. Min Act: -0.0001

Data Index: 801815 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.7560. Min Range: -0.7560

Max Act: 0.6470. Min Act: -0.0001

Data Index: 111712 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.7560. Min Range: -0.7560

Max Act: 0.6388. Min Act: -0.0001

Data Index: 1578884 (Python Code)

Max Activating Token Index: 775

Text #12

Max Range: 0.7560. Min Range: -0.7560

Max Act: 0.6308. Min Act: -0.0001

Data Index: 1203793 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.7560. Min Range: -0.7560

Max Act: 0.6342. Min Act: -0.0001

Data Index: 428986 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 0.7560. Min Range: -0.7560

Max Act: 0.6074. Min Act: -0.0001

Data Index: 1349485 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 0.7560. Min Range: -0.7560

Max Act: 0.6255. Min Act: -0.0001

Data Index: 802938 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 0.7560. Min Range: -0.7560

Max Act: 0.6618. Min Act: -0.0001

Data Index: 317168 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.7560. Min Range: -0.7560

Max Act: 0.6280. Min Act: -0.0001

Data Index: 1242591 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.7560. Min Range: -0.7560

Max Act: 0.5931. Min Act: -0.0001

Data Index: 1452061 (Python Code)

Max Activating Token Index: 655

Text #19

Max Range: 0.7560. Min Range: -0.7560

Max Act: 0.5900. Min Act: -0.0001

Data Index: 1137719 (C4 (Web Text))

Max Activating Token Index: 1017