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

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

Neuron 543 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: 1.8450. Min Range: -1.8450

Max Act: 1.8450. Min Act: -0.0003

Data Index: 662715 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 1.8450. Min Range: -1.8450

Max Act: 1.7225. Min Act: -0.0002

Data Index: 880332 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 1.8450. Min Range: -1.8450

Max Act: 1.6984. Min Act: -0.0002

Data Index: 581032 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 1.8450. Min Range: -1.8450

Max Act: 1.7209. Min Act: -0.0002

Data Index: 1136206 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 1.8450. Min Range: -1.8450

Max Act: 1.7531. Min Act: -0.0002

Data Index: 364275 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 1.8450. Min Range: -1.8450

Max Act: 1.6795. Min Act: -0.0002

Data Index: 108799 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 1.8450. Min Range: -1.8450

Max Act: 1.7792. Min Act: -0.0002

Data Index: 370248 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 1.8450. Min Range: -1.8450

Max Act: 1.6700. Min Act: -0.0002

Data Index: 1267124 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 1.8450. Min Range: -1.8450

Max Act: 1.6864. Min Act: -0.0002

Data Index: 1302070 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 1.8450. Min Range: -1.8450

Max Act: 1.6730. Min Act: -0.0002

Data Index: 317110 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 1.8450. Min Range: -1.8450

Max Act: 1.5966. Min Act: -0.0002

Data Index: 382292 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 1.8450. Min Range: -1.8450

Max Act: 1.6026. Min Act: -0.0002

Data Index: 251016 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 1.8450. Min Range: -1.8450

Max Act: 1.6022. Min Act: -0.0002

Data Index: 1079897 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 1.8450. Min Range: -1.8450

Max Act: 1.6176. Min Act: -0.0002

Data Index: 740575 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 1.8450. Min Range: -1.8450

Max Act: 1.6125. Min Act: -0.0002

Data Index: 723342 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 1.8450. Min Range: -1.8450

Max Act: 1.5687. Min Act: -0.0002

Data Index: 1354316 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 1.8450. Min Range: -1.8450

Max Act: 1.5946. Min Act: -0.0002

Data Index: 1141453 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 1.8450. Min Range: -1.8450

Max Act: 1.5633. Min Act: -0.0002

Data Index: 1058193 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 1.8450. Min Range: -1.8450

Max Act: 1.6365. Min Act: -0.0002

Data Index: 1180395 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 1.8450. Min Range: -1.8450

Max Act: 1.6320. Min Act: -0.0003

Data Index: 1074308 (C4 (Web Text))

Max Activating Token Index: 218