Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 280 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0162. Min Act: -0.0004

Data Index: 1542720 (Python Code)

Max Activating Token Index: 876

Text #1

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0161. Min Act: -0.0004

Data Index: 71635 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0159. Min Act: -0.0004

Data Index: 1245389 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0158. Min Act: -0.0004

Data Index: 1039394 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0147. Min Act: -0.0004

Data Index: 253104 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0149. Min Act: -0.0004

Data Index: 62603 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0149. Min Act: -0.0004

Data Index: 1318510 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0148. Min Act: -0.0004

Data Index: 731443 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0145. Min Act: -0.0004

Data Index: 1238952 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0144. Min Act: -0.0005

Data Index: 672011 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0144. Min Act: -0.0004

Data Index: 1646099 (Python Code)

Max Activating Token Index: 13

Text #11

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0145. Min Act: -0.0004

Data Index: 400480 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0142. Min Act: -0.0004

Data Index: 385077 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0143. Min Act: -0.0005

Data Index: 39903 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0142. Min Act: -0.0005

Data Index: 56587 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0142. Min Act: -0.0004

Data Index: 593465 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0145. Min Act: -0.0004

Data Index: 1218207 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0138. Min Act: -0.0005

Data Index: 983894 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0140. Min Act: -0.0005

Data Index: 883294 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0144. Min Act: -0.0004

Data Index: 1173446 (C4 (Web Text))

Max Activating Token Index: 897