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

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

Neuron 5092 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: 0.6306. Min Range: -0.6306

Max Act: 0.6306. Min Act: -0.0002

Data Index: 45881 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.6297. Min Act: -0.0002

Data Index: 30015 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.6201. Min Act: -0.0002

Data Index: 1247877 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5577. Min Act: -0.0002

Data Index: 1007580 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5557. Min Act: -0.0002

Data Index: 51672 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5543. Min Act: -0.0002

Data Index: 911252 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5486. Min Act: -0.0002

Data Index: 1307797 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5255. Min Act: -0.0002

Data Index: 789888 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5296. Min Act: -0.0002

Data Index: 501879 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5259. Min Act: -0.0002

Data Index: 518666 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5260. Min Act: -0.0002

Data Index: 1072228 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5243. Min Act: -0.0002

Data Index: 433731 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5114. Min Act: -0.0002

Data Index: 248984 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5266. Min Act: -0.0002

Data Index: 1074425 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5105. Min Act: -0.0002

Data Index: 1103884 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5013. Min Act: -0.0002

Data Index: 290664 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4925. Min Act: -0.0002

Data Index: 403263 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5023. Min Act: -0.0002

Data Index: 661517 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.5087. Min Act: -0.0003

Data Index: 1172177 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4922. Min Act: -0.0002

Data Index: 795178 (C4 (Web Text))

Max Activating Token Index: 759