Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 430 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0184. Min Act: -0.0001

Data Index: 972845 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0193. Min Act: -0.0001

Data Index: 1334477 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0176. Min Act: -0.0001

Data Index: 80834 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0154. Min Act: -0.0001

Data Index: 1212557 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0157. Min Act: -0.0001

Data Index: 297974 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0134. Min Act: -0.0001

Data Index: 2341 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0140. Min Act: -0.0001

Data Index: 94721 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0145. Min Act: -0.0001

Data Index: 172790 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0147. Min Act: -0.0001

Data Index: 1016208 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0147. Min Act: -0.0001

Data Index: 151467 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0135. Min Act: -0.0001

Data Index: 193054 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0128. Min Act: -0.0001

Data Index: 502315 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0142. Min Act: -0.0001

Data Index: 131355 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0134. Min Act: -0.0001

Data Index: 881755 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0143. Min Act: -0.0001

Data Index: 1477727 (Python Code)

Max Activating Token Index: 491

Text #15

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0132. Min Act: -0.0001

Data Index: 331602 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0128. Min Act: -0.0001

Data Index: 747708 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0128. Min Act: -0.0001

Data Index: 1102384 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0129. Min Act: -0.0001

Data Index: 825229 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.0193. Min Range: -0.0193

Max Act: 0.0115. Min Act: -0.0001

Data Index: 1230065 (C4 (Web Text))

Max Activating Token Index: 380