Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1215 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0434. Min Act: -0.0005

Data Index: 1010139 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0341. Min Act: -0.0005

Data Index: 990061 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0353. Min Act: -0.0005

Data Index: 834079 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0329. Min Act: -0.0005

Data Index: 1201757 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0330. Min Act: -0.0005

Data Index: 3663 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0315. Min Act: -0.0005

Data Index: 740743 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0305. Min Act: -0.0005

Data Index: 405491 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0298. Min Act: -0.0005

Data Index: 1147058 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0309. Min Act: -0.0005

Data Index: 345371 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0297. Min Act: -0.0005

Data Index: 785500 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0302. Min Act: -0.0005

Data Index: 162772 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0295. Min Act: -0.0005

Data Index: 97034 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0300. Min Act: -0.0005

Data Index: 412943 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0287. Min Act: -0.0005

Data Index: 475472 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0285. Min Act: -0.0005

Data Index: 907281 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0291. Min Act: -0.0005

Data Index: 641943 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0245. Min Act: -0.0005

Data Index: 1104368 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0293. Min Act: -0.0005

Data Index: 434315 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0286. Min Act: -0.0005

Data Index: 1211862 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0274. Min Act: -0.0005

Data Index: 783780 (C4 (Web Text))

Max Activating Token Index: 500