Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1509 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0164. Min Act: -0.0006

Data Index: 849556 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0155. Min Act: -0.0006

Data Index: 135529 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0154. Min Act: -0.0006

Data Index: 304310 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0154. Min Act: -0.0006

Data Index: 343623 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0152. Min Act: -0.0006

Data Index: 545822 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0151. Min Act: -0.0006

Data Index: 629183 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0151. Min Act: -0.0006

Data Index: 752422 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0148. Min Act: -0.0006

Data Index: 402818 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0149. Min Act: -0.0006

Data Index: 290094 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0146. Min Act: -0.0006

Data Index: 650054 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1339707 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0144. Min Act: -0.0006

Data Index: 1267890 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0141. Min Act: -0.0006

Data Index: 1091715 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1102466 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0140. Min Act: -0.0006

Data Index: 124281 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0143. Min Act: -0.0006

Data Index: 963663 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0146. Min Act: -0.0006

Data Index: 760456 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0143. Min Act: -0.0006

Data Index: 617773 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0145. Min Act: -0.0006

Data Index: 852762 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0141. Min Act: -0.0006

Data Index: 305033 (C4 (Web Text))

Max Activating Token Index: 1023