Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 508 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0871. Min Range: -1.0871

Max Act: 1.0871. Min Act: -0.0001

Data Index: 299060 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 1.0871. Min Range: -1.0871

Max Act: 1.0441. Min Act: -0.0001

Data Index: 962772 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 1.0871. Min Range: -1.0871

Max Act: 1.0443. Min Act: -0.0001

Data Index: 369971 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.9210. Min Act: -0.0001

Data Index: 463364 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.9859. Min Act: -0.0001

Data Index: 1049810 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.9803. Min Act: -0.0001

Data Index: 621586 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.9625. Min Act: -0.0001

Data Index: 104088 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.8603. Min Act: -0.0001

Data Index: 1330187 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.9847. Min Act: -0.0001

Data Index: 1139058 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.8899. Min Act: -0.0001

Data Index: 1184655 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.9306. Min Act: -0.0001

Data Index: 515880 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.8636. Min Act: -0.0001

Data Index: 1055195 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.8725. Min Act: -0.0001

Data Index: 982289 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.8290. Min Act: -0.0001

Data Index: 542188 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.8172. Min Act: -0.0001

Data Index: 735926 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.8573. Min Act: -0.0001

Data Index: 1119734 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.8753. Min Act: -0.0001

Data Index: 635090 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.8395. Min Act: -0.0001

Data Index: 951130 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.8376. Min Act: -0.0001

Data Index: 801318 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.8533. Min Act: -0.0001

Data Index: 52955 (C4 (Web Text))

Max Activating Token Index: 610