Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 92 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.9273. Min Act: -0.0001

Data Index: 265543 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.9221. Min Act: -0.0001

Data Index: 895515 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.9005. Min Act: -0.0001

Data Index: 370252 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.8421. Min Act: -0.0001

Data Index: 1096142 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.8101. Min Act: -0.0001

Data Index: 1184269 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.8056. Min Act: -0.0001

Data Index: 705272 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.8236. Min Act: -0.0001

Data Index: 192088 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.7888. Min Act: -0.0001

Data Index: 572223 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.7986. Min Act: -0.0001

Data Index: 264736 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.7939. Min Act: -0.0001

Data Index: 1029070 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.8055. Min Act: -0.0001

Data Index: 1172476 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.8442. Min Act: -0.0001

Data Index: 758175 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.8003. Min Act: -0.0001

Data Index: 723581 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.7268. Min Act: -0.0001

Data Index: 1198965 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.7456. Min Act: -0.0001

Data Index: 698838 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.7183. Min Act: -0.0001

Data Index: 759224 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.7321. Min Act: -0.0001

Data Index: 756861 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.7490. Min Act: -0.0001

Data Index: 1383873 (Python Code)

Max Activating Token Index: 51

Text #18

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.7286. Min Act: -0.0001

Data Index: 948568 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.9273. Min Range: -0.9273

Max Act: 0.7264. Min Act: -0.0001

Data Index: 1282645 (C4 (Web Text))

Max Activating Token Index: 57