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

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

Neuron 328 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3509. Min Range: -4.3509

Max Act: 4.3183. Min Act: -0.0000

Data Index: 801479 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 4.3509. Min Range: -4.3509

Max Act: 4.3509. Min Act: -0.0000

Data Index: 1332330 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 4.3509. Min Range: -4.3509

Max Act: 3.8993. Min Act: -0.0000

Data Index: 1154536 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 4.3509. Min Range: -4.3509

Max Act: 3.8498. Min Act: -0.0000

Data Index: 2380 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 4.3509. Min Range: -4.3509

Max Act: 3.9768. Min Act: -0.0000

Data Index: 552629 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 4.3509. Min Range: -4.3509

Max Act: 3.8481. Min Act: -0.0000

Data Index: 806677 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 4.3509. Min Range: -4.3509

Max Act: 3.6603. Min Act: -0.0000

Data Index: 920637 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 4.3509. Min Range: -4.3509

Max Act: 3.6349. Min Act: -0.0000

Data Index: 1017443 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 4.3509. Min Range: -4.3509

Max Act: 3.5760. Min Act: -0.0000

Data Index: 1180871 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 4.3509. Min Range: -4.3509

Max Act: 3.4941. Min Act: -0.0000

Data Index: 175703 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 4.3509. Min Range: -4.3509

Max Act: 3.6011. Min Act: -0.0000

Data Index: 368043 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 4.3509. Min Range: -4.3509

Max Act: 3.2542. Min Act: -0.0000

Data Index: 1124808 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 4.3509. Min Range: -4.3509

Max Act: 3.4161. Min Act: -0.0001

Data Index: 871508 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 4.3509. Min Range: -4.3509

Max Act: 3.4160. Min Act: -0.0000

Data Index: 464234 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 4.3509. Min Range: -4.3509

Max Act: 3.2562. Min Act: -0.0000

Data Index: 433176 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 4.3509. Min Range: -4.3509

Max Act: 3.5329. Min Act: -0.0000

Data Index: 212573 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 4.3509. Min Range: -4.3509

Max Act: 3.3536. Min Act: -0.0000

Data Index: 709576 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 4.3509. Min Range: -4.3509

Max Act: 3.1980. Min Act: -0.0000

Data Index: 966795 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 4.3509. Min Range: -4.3509

Max Act: 3.3051. Min Act: -0.0000

Data Index: 637571 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 4.3509. Min Range: -4.3509

Max Act: 3.4467. Min Act: -0.0000

Data Index: 1349130 (C4 (Web Text))

Max Activating Token Index: 326