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

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

Neuron 1133 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: 0.0155. Min Range: -0.0155

Max Act: 0.0154. Min Act: -0.0006

Data Index: 324069 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0155. Min Act: -0.0006

Data Index: 541874 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1156908 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0154. Min Act: -0.0006

Data Index: 557271 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0153. Min Act: -0.0006

Data Index: 941120 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0153. Min Act: -0.0006

Data Index: 746939 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1337821 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0152. Min Act: -0.0006

Data Index: 60923 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0152. Min Act: -0.0006

Data Index: 486743 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0151. Min Act: -0.0006

Data Index: 1172439 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0151. Min Act: -0.0006

Data Index: 1091342 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1099470 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0148. Min Act: -0.0007

Data Index: 977360 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0150. Min Act: -0.0006

Data Index: 968926 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0150. Min Act: -0.0006

Data Index: 270047 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0146. Min Act: -0.0006

Data Index: 932723 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0148. Min Act: -0.0007

Data Index: 1301931 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1077402 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0147. Min Act: -0.0006

Data Index: 554734 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0149. Min Act: -0.0006

Data Index: 1132394 (C4 (Web Text))

Max Activating Token Index: 123