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

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

Neuron 1476 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0195. Min Act: -0.0006

Data Index: 1251460 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0183. Min Act: -0.0006

Data Index: 1466669 (Python Code)

Max Activating Token Index: 285

Text #2

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0154. Min Act: -0.0006

Data Index: 898362 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0160. Min Act: -0.0006

Data Index: 1282407 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0165. Min Act: -0.0006

Data Index: 802778 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1560377 (Python Code)

Max Activating Token Index: 35

Text #6

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0140. Min Act: -0.0006

Data Index: 431910 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0152. Min Act: -0.0006

Data Index: 468513 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0144. Min Act: -0.0005

Data Index: 1619021 (Python Code)

Max Activating Token Index: 886

Text #9

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0147. Min Act: -0.0006

Data Index: 1206621 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0145. Min Act: -0.0006

Data Index: 382276 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1492447 (Python Code)

Max Activating Token Index: 585

Text #12

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1173503 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1268450 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0140. Min Act: -0.0006

Data Index: 867841 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0143. Min Act: -0.0006

Data Index: 391572 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0141. Min Act: -0.0006

Data Index: 1369408 (Python Code)

Max Activating Token Index: 105

Text #17

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0137. Min Act: -0.0006

Data Index: 844481 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0140. Min Act: -0.0006

Data Index: 553135 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0130. Min Act: -0.0006

Data Index: 959518 (C4 (Web Text))

Max Activating Token Index: 897