Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1945 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9131. Min Range: -0.9131

Max Act: 0.9131. Min Act: -0.0000

Data Index: 792466 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.9131. Min Range: -0.9131

Max Act: 0.8790. Min Act: -0.0000

Data Index: 876294 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.9131. Min Range: -0.9131

Max Act: 0.7971. Min Act: -0.0000

Data Index: 670797 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 0.9131. Min Range: -0.9131

Max Act: 0.7908. Min Act: -0.0000

Data Index: 1349521 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 0.9131. Min Range: -0.9131

Max Act: 0.7892. Min Act: -0.0000

Data Index: 544883 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.9131. Min Range: -0.9131

Max Act: 0.6576. Min Act: -0.0000

Data Index: 767361 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.9131. Min Range: -0.9131

Max Act: 0.5836. Min Act: -0.0000

Data Index: 130239 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.9131. Min Range: -0.9131

Max Act: 0.6169. Min Act: -0.0000

Data Index: 32146 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.9131. Min Range: -0.9131

Max Act: 0.6313. Min Act: -0.0000

Data Index: 445875 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 0.9131. Min Range: -0.9131

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1143567 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 0.9131. Min Range: -0.9131

Max Act: 0.6150. Min Act: -0.0000

Data Index: 453422 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.9131. Min Range: -0.9131

Max Act: 0.5509. Min Act: -0.0000

Data Index: 462213 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 0.9131. Min Range: -0.9131

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1212227 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.9131. Min Range: -0.9131

Max Act: 0.5781. Min Act: -0.0000

Data Index: 998327 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.9131. Min Range: -0.9131

Max Act: 0.5531. Min Act: -0.0000

Data Index: 1182178 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.9131. Min Range: -0.9131

Max Act: 0.5560. Min Act: -0.0000

Data Index: 455099 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.9131. Min Range: -0.9131

Max Act: 0.5814. Min Act: -0.0000

Data Index: 1079046 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.9131. Min Range: -0.9131

Max Act: 0.5583. Min Act: -0.0000

Data Index: 1103582 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 0.9131. Min Range: -0.9131

Max Act: 0.5512. Min Act: -0.0000

Data Index: 941677 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 0.9131. Min Range: -0.9131

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1343466 (C4 (Web Text))

Max Activating Token Index: 47