Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 987 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0196. Min Act: -0.0006

Data Index: 1082667 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0162. Min Act: -0.0006

Data Index: 237998 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0157. Min Act: -0.0006

Data Index: 1249538 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0147. Min Act: -0.0006

Data Index: 1285418 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0150. Min Act: -0.0006

Data Index: 72409 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1098780 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0153. Min Act: -0.0005

Data Index: 734061 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0154. Min Act: -0.0006

Data Index: 103916 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1353811 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0157. Min Act: -0.0006

Data Index: 385442 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0140. Min Act: -0.0005

Data Index: 927528 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0149. Min Act: -0.0006

Data Index: 447097 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0149. Min Act: -0.0006

Data Index: 1560792 (Python Code)

Max Activating Token Index: 82

Text #13

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0148. Min Act: -0.0005

Data Index: 1369096 (Python Code)

Max Activating Token Index: 99

Text #14

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0142. Min Act: -0.0006

Data Index: 692389 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1056045 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1213514 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1267147 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0148. Min Act: -0.0006

Data Index: 117113 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0140. Min Act: -0.0006

Data Index: 524964 (C4 (Web Text))

Max Activating Token Index: 276