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

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

Neuron 1758 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: 0.0165. Min Range: -0.0165

Max Act: 0.0165. Min Act: -0.0002

Data Index: 1014773 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0148. Min Act: -0.0001

Data Index: 1263380 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1316310 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1237397 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0138. Min Act: -0.0002

Data Index: 121696 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1593720 (Python Code)

Max Activating Token Index: 745

Text #6

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0130. Min Act: -0.0001

Data Index: 176451 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0128. Min Act: -0.0002

Data Index: 366097 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1052362 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0124. Min Act: -0.0002

Data Index: 186895 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0124. Min Act: -0.0002

Data Index: 39918 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0122. Min Act: -0.0002

Data Index: 504543 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0121. Min Act: -0.0002

Data Index: 1127104 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1335161 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0108. Min Act: -0.0002

Data Index: 493683 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0107. Min Act: -0.0002

Data Index: 504642 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0106. Min Act: -0.0002

Data Index: 811904 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0107. Min Act: -0.0002

Data Index: 212099 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0105. Min Act: -0.0002

Data Index: 630538 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 0.0165. Min Range: -0.0165

Max Act: 0.0104. Min Act: -0.0002

Data Index: 1088484 (C4 (Web Text))

Max Activating Token Index: 597