Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1502 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0176. Min Act: -0.0005

Data Index: 422476 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0177. Min Act: -0.0005

Data Index: 821166 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0156. Min Act: -0.0005

Data Index: 85500 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0153. Min Act: -0.0005

Data Index: 1238397 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0151. Min Act: -0.0005

Data Index: 433810 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0157. Min Act: -0.0005

Data Index: 1099777 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0160. Min Act: -0.0005

Data Index: 1279693 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0147. Min Act: -0.0005

Data Index: 763442 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0144. Min Act: -0.0005

Data Index: 167011 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0146. Min Act: -0.0005

Data Index: 551894 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0145. Min Act: -0.0005

Data Index: 207962 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0145. Min Act: -0.0005

Data Index: 45576 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0150. Min Act: -0.0005

Data Index: 284919 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0143. Min Act: -0.0005

Data Index: 392649 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0142. Min Act: -0.0005

Data Index: 762711 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0137. Min Act: -0.0005

Data Index: 276784 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0142. Min Act: -0.0005

Data Index: 634385 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0143. Min Act: -0.0005

Data Index: 564653 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0131. Min Act: -0.0005

Data Index: 221055 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0134. Min Act: -0.0005

Data Index: 10498 (C4 (Web Text))

Max Activating Token Index: 912