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

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

Neuron 226 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.7165. Min Act: -0.0000

Data Index: 379411 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.5275. Min Act: 0.0000

Data Index: 255456 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.6135. Min Act: -0.0000

Data Index: 784273 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.2715. Min Act: -0.0000

Data Index: 986158 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.1142. Min Act: -0.0000

Data Index: 633258 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.2520. Min Act: -0.0000

Data Index: 892824 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.1173. Min Act: 0.0000

Data Index: 1285180 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.0416. Min Act: -0.0000

Data Index: 1208381 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.1085. Min Act: -0.0000

Data Index: 568266 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.1061. Min Act: -0.0000

Data Index: 851659 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.1022. Min Act: -0.0000

Data Index: 960215 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.0955. Min Act: -0.0000

Data Index: 996100 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.0946. Min Act: -0.0000

Data Index: 282283 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.9869. Min Act: -0.0000

Data Index: 950281 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.0179. Min Act: -0.0000

Data Index: 12315 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.0630. Min Act: -0.0000

Data Index: 681709 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.9418. Min Act: -0.0000

Data Index: 471381 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.9894. Min Act: -0.0000

Data Index: 681529 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.9346. Min Act: 0.0000

Data Index: 722619 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 1.7165. Min Range: -1.7165

Max Act: 0.9324. Min Act: -0.0000

Data Index: 1123843 (C4 (Web Text))

Max Activating Token Index: 29