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

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

Neuron 5713 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.0006. Min Range: -1.0006

Max Act: 1.0006. Min Act: -0.0002

Data Index: 597834 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.9477. Min Act: -0.0002

Data Index: 871124 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.9560. Min Act: -0.0002

Data Index: 143589 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.9570. Min Act: -0.0002

Data Index: 1024979 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.9376. Min Act: -0.0002

Data Index: 532735 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.9408. Min Act: -0.0002

Data Index: 1102809 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.9548. Min Act: -0.0002

Data Index: 1279060 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.9279. Min Act: -0.0002

Data Index: 1294536 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.9330. Min Act: -0.0002

Data Index: 279811 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.9195. Min Act: -0.0002

Data Index: 459311 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.9096. Min Act: -0.0002

Data Index: 269850 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.9020. Min Act: -0.0002

Data Index: 393352 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.9023. Min Act: -0.0002

Data Index: 725535 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.8877. Min Act: -0.0002

Data Index: 1305471 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.8804. Min Act: -0.0002

Data Index: 1129630 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.8913. Min Act: -0.0002

Data Index: 751706 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.8941. Min Act: -0.0002

Data Index: 177249 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.9092. Min Act: -0.0002

Data Index: 644708 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.8516. Min Act: -0.0002

Data Index: 1031983 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 1.0006. Min Range: -1.0006

Max Act: 0.8664. Min Act: -0.0002

Data Index: 1026243 (C4 (Web Text))

Max Activating Token Index: 802