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

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

Neuron 1784 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0191. Min Act: -0.0002

Data Index: 1363083 (Python Code)

Max Activating Token Index: 154

Text #1

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0182. Min Act: -0.0003

Data Index: 1562832 (Python Code)

Max Activating Token Index: 674

Text #2

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0174. Min Act: -0.0002

Data Index: 1559150 (Python Code)

Max Activating Token Index: 173

Text #3

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1594675 (Python Code)

Max Activating Token Index: 897

Text #4

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0167. Min Act: -0.0003

Data Index: 1525090 (Python Code)

Max Activating Token Index: 659

Text #5

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1505959 (Python Code)

Max Activating Token Index: 294

Text #6

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0152. Min Act: -0.0002

Data Index: 1463995 (Python Code)

Max Activating Token Index: 674

Text #7

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1543092 (Python Code)

Max Activating Token Index: 217

Text #8

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0160. Min Act: -0.0003

Data Index: 1640137 (Python Code)

Max Activating Token Index: 608

Text #9

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1385680 (Python Code)

Max Activating Token Index: 237

Text #10

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1544816 (Python Code)

Max Activating Token Index: 189

Text #11

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0141. Min Act: -0.0003

Data Index: 1397519 (Python Code)

Max Activating Token Index: 325

Text #12

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1493125 (Python Code)

Max Activating Token Index: 353

Text #13

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0134. Min Act: -0.0003

Data Index: 1430504 (Python Code)

Max Activating Token Index: 525

Text #14

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0131. Min Act: -0.0002

Data Index: 518646 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0123. Min Act: -0.0003

Data Index: 1369633 (Python Code)

Max Activating Token Index: 317

Text #16

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0125. Min Act: -0.0001

Data Index: 1572420 (Python Code)

Max Activating Token Index: 579

Text #17

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0124. Min Act: -0.0003

Data Index: 1489558 (Python Code)

Max Activating Token Index: 542

Text #18

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1558023 (Python Code)

Max Activating Token Index: 143

Text #19

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0120. Min Act: -0.0002

Data Index: 1556203 (Python Code)

Max Activating Token Index: 1018