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

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

Neuron 1951 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1242. Min Range: -2.1242

Max Act: 2.1242. Min Act: -0.0000

Data Index: 508773 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 2.1242. Min Range: -2.1242

Max Act: 1.5412. Min Act: -0.0000

Data Index: 208375 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 2.1242. Min Range: -2.1242

Max Act: 1.6727. Min Act: -0.0000

Data Index: 828218 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 2.1242. Min Range: -2.1242

Max Act: 1.7093. Min Act: -0.0000

Data Index: 1120179 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 2.1242. Min Range: -2.1242

Max Act: 1.4903. Min Act: -0.0000

Data Index: 1332042 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 2.1242. Min Range: -2.1242

Max Act: 1.3597. Min Act: -0.0000

Data Index: 109609 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 2.1242. Min Range: -2.1242

Max Act: 1.5208. Min Act: -0.0000

Data Index: 509080 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 2.1242. Min Range: -2.1242

Max Act: 1.4168. Min Act: -0.0000

Data Index: 231193 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 2.1242. Min Range: -2.1242

Max Act: 1.3984. Min Act: -0.0000

Data Index: 973992 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 2.1242. Min Range: -2.1242

Max Act: 1.4048. Min Act: -0.0000

Data Index: 18205 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 2.1242. Min Range: -2.1242

Max Act: 1.2342. Min Act: -0.0000

Data Index: 514778 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 2.1242. Min Range: -2.1242

Max Act: 1.3656. Min Act: -0.0000

Data Index: 848038 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 2.1242. Min Range: -2.1242

Max Act: 1.2686. Min Act: -0.0000

Data Index: 276471 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 2.1242. Min Range: -2.1242

Max Act: 1.2669. Min Act: -0.0000

Data Index: 1269587 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 2.1242. Min Range: -2.1242

Max Act: 1.2392. Min Act: -0.0000

Data Index: 560697 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 2.1242. Min Range: -2.1242

Max Act: 1.2112. Min Act: -0.0000

Data Index: 942680 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 2.1242. Min Range: -2.1242

Max Act: 1.1892. Min Act: -0.0000

Data Index: 604740 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 2.1242. Min Range: -2.1242

Max Act: 1.1814. Min Act: -0.0000

Data Index: 695967 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 2.1242. Min Range: -2.1242

Max Act: 1.1536. Min Act: -0.0000

Data Index: 1287059 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 2.1242. Min Range: -2.1242

Max Act: 1.1483. Min Act: -0.0000

Data Index: 1195524 (C4 (Web Text))

Max Activating Token Index: 260