Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1119 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0219. Min Act: -0.0001

Data Index: 799988 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0186. Min Act: -0.0001

Data Index: 738763 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0171. Min Act: -0.0001

Data Index: 1163788 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0183. Min Act: -0.0001

Data Index: 685462 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0161. Min Act: -0.0001

Data Index: 1554043 (Python Code)

Max Activating Token Index: 134

Text #5

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0169. Min Act: -0.0001

Data Index: 807174 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0166. Min Act: -0.0001

Data Index: 164451 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0157. Min Act: -0.0001

Data Index: 1606513 (Python Code)

Max Activating Token Index: 566

Text #8

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0160. Min Act: -0.0001

Data Index: 1135443 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0143. Min Act: -0.0001

Data Index: 731562 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0154. Min Act: -0.0000

Data Index: 300032 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0140. Min Act: -0.0001

Data Index: 159721 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0149. Min Act: -0.0001

Data Index: 1542109 (Python Code)

Max Activating Token Index: 415

Text #13

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0144. Min Act: -0.0001

Data Index: 325392 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0142. Min Act: -0.0001

Data Index: 1236192 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0146. Min Act: -0.0000

Data Index: 1141414 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0138. Min Act: -0.0001

Data Index: 1431693 (Python Code)

Max Activating Token Index: 214

Text #17

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0144. Min Act: -0.0001

Data Index: 1260235 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0147. Min Act: -0.0001

Data Index: 1293332 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0139. Min Act: -0.0001

Data Index: 305950 (C4 (Web Text))

Max Activating Token Index: 247