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

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

Neuron 5078 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.9890. Min Act: -0.0000

Data Index: 769141 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.9172. Min Act: -0.0000

Data Index: 718239 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.9503. Min Act: -0.0000

Data Index: 950395 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.9432. Min Act: -0.0000

Data Index: 649956 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.8942. Min Act: -0.0000

Data Index: 1036114 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.9160. Min Act: -0.0000

Data Index: 657461 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1297321 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.8821. Min Act: -0.0000

Data Index: 909880 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.8783. Min Act: 0.0000

Data Index: 298775 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.7422. Min Act: -0.0000

Data Index: 742715 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.7854. Min Act: -0.0000

Data Index: 349410 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.7977. Min Act: -0.0000

Data Index: 869972 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.7775. Min Act: -0.0000

Data Index: 24629 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.7745. Min Act: -0.0000

Data Index: 743843 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.7647. Min Act: 0.0000

Data Index: 1165076 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.7541. Min Act: 0.0000

Data Index: 876458 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.7344. Min Act: -0.0000

Data Index: 900131 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.6948. Min Act: -0.0000

Data Index: 42173 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.6635. Min Act: -0.0000

Data Index: 555853 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.9890. Min Range: -0.9890

Max Act: 0.6538. Min Act: -0.0000

Data Index: 376599 (C4 (Web Text))

Max Activating Token Index: 931