Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 898 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0190. Min Act: -0.0003

Data Index: 191990 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0182. Min Act: -0.0003

Data Index: 436582 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0180. Min Act: -0.0003

Data Index: 24516 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0176. Min Act: -0.0003

Data Index: 875983 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0173. Min Act: -0.0003

Data Index: 1331192 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0165. Min Act: -0.0003

Data Index: 1530387 (Python Code)

Max Activating Token Index: 957

Text #6

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0167. Min Act: -0.0003

Data Index: 249299 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0166. Min Act: -0.0003

Data Index: 866954 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0167. Min Act: -0.0003

Data Index: 974695 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0166. Min Act: -0.0003

Data Index: 948569 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0163. Min Act: -0.0003

Data Index: 815604 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0163. Min Act: -0.0003

Data Index: 1197972 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0163. Min Act: -0.0003

Data Index: 1046479 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0163. Min Act: -0.0003

Data Index: 1334330 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0159. Min Act: -0.0003

Data Index: 323632 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0159. Min Act: -0.0003

Data Index: 1046303 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0160. Min Act: -0.0003

Data Index: 1358124 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0160. Min Act: -0.0003

Data Index: 1602115 (Python Code)

Max Activating Token Index: 901

Text #18

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0158. Min Act: -0.0003

Data Index: 570616 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0160. Min Act: -0.0003

Data Index: 125496 (C4 (Web Text))

Max Activating Token Index: 790