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

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

Neuron 328 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: 0.0162. Min Range: -0.0162

Max Act: 0.0149. Min Act: -0.0006

Data Index: 1546494 (Python Code)

Max Activating Token Index: 8

Text #1

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0162. Min Act: -0.0006

Data Index: 1445184 (Python Code)

Max Activating Token Index: 194

Text #2

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0147. Min Act: -0.0005

Data Index: 687188 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0143. Min Act: -0.0005

Data Index: 325494 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0156. Min Act: -0.0006

Data Index: 220275 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0160. Min Act: -0.0005

Data Index: 165744 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0139. Min Act: -0.0006

Data Index: 584694 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0141. Min Act: -0.0006

Data Index: 1525657 (Python Code)

Max Activating Token Index: 733

Text #8

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0145. Min Act: -0.0006

Data Index: 1523190 (Python Code)

Max Activating Token Index: 222

Text #9

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0144. Min Act: -0.0006

Data Index: 1395840 (Python Code)

Max Activating Token Index: 8

Text #10

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1488366 (Python Code)

Max Activating Token Index: 201

Text #11

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0147. Min Act: -0.0006

Data Index: 1117460 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0137. Min Act: -0.0005

Data Index: 511542 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0136. Min Act: -0.0005

Data Index: 1210898 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0151. Min Act: -0.0005

Data Index: 575587 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0119. Min Act: -0.0006

Data Index: 103996 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0128. Min Act: -0.0006

Data Index: 1640658 (Python Code)

Max Activating Token Index: 808

Text #17

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0139. Min Act: -0.0005

Data Index: 677069 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0142. Min Act: -0.0005

Data Index: 833999 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0138. Min Act: -0.0006

Data Index: 267587 (C4 (Web Text))

Max Activating Token Index: 289