Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1975 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0210. Min Act: -0.0002

Data Index: 932458 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0164. Min Act: -0.0002

Data Index: 692855 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0163. Min Act: -0.0002

Data Index: 566052 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1435307 (Python Code)

Max Activating Token Index: 637

Text #4

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0156. Min Act: -0.0002

Data Index: 589564 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0143. Min Act: -0.0002

Data Index: 601235 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0143. Min Act: -0.0002

Data Index: 475249 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0143. Min Act: -0.0002

Data Index: 784991 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0142. Min Act: -0.0002

Data Index: 834517 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0139. Min Act: -0.0002

Data Index: 104046 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0137. Min Act: -0.0002

Data Index: 564332 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0141. Min Act: -0.0002

Data Index: 786351 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0138. Min Act: -0.0002

Data Index: 586717 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0137. Min Act: -0.0002

Data Index: 944137 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1029174 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0138. Min Act: -0.0002

Data Index: 844984 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0136. Min Act: -0.0002

Data Index: 352929 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0127. Min Act: -0.0002

Data Index: 520131 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1487489 (Python Code)

Max Activating Token Index: 320

Text #19

Max Range: 0.0210. Min Range: -0.0210

Max Act: 0.0132. Min Act: -0.0002

Data Index: 284171 (C4 (Web Text))

Max Activating Token Index: 870