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

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

Neuron 3605 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: 1.1285. Min Range: -1.1285

Max Act: 1.1253. Min Act: -0.0002

Data Index: 924978 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.1285. Min Act: -0.0002

Data Index: 291051 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0972. Min Act: -0.0002

Data Index: 664409 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0869. Min Act: -0.0002

Data Index: 783258 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0510. Min Act: -0.0002

Data Index: 736975 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0366. Min Act: -0.0002

Data Index: 779272 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0124. Min Act: -0.0002

Data Index: 135159 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0070. Min Act: -0.0003

Data Index: 317687 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0066. Min Act: -0.0002

Data Index: 1339474 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9903. Min Act: -0.0003

Data Index: 135924 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 1.1285. Min Range: -1.1285

Max Act: 1.0094. Min Act: -0.0003

Data Index: 138493 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9710. Min Act: -0.0002

Data Index: 1261911 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9728. Min Act: -0.0002

Data Index: 930788 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9790. Min Act: -0.0002

Data Index: 85115 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9740. Min Act: -0.0002

Data Index: 1336533 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9430. Min Act: -0.0002

Data Index: 530596 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9406. Min Act: -0.0002

Data Index: 266155 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9389. Min Act: -0.0002

Data Index: 156202 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9353. Min Act: -0.0002

Data Index: 794931 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 1.1285. Min Range: -1.1285

Max Act: 0.9569. Min Act: -0.0002

Data Index: 1255744 (C4 (Web Text))

Max Activating Token Index: 694