Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5181 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0170. Min Act: -0.0001

Data Index: 53216 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0165. Min Act: -0.0001

Data Index: 901944 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0160. Min Act: -0.0001

Data Index: 1043734 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0157. Min Act: -0.0001

Data Index: 1190473 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1654699 (Python Code)

Max Activating Token Index: 789

Text #5

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0157. Min Act: -0.0001

Data Index: 140018 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0154. Min Act: -0.0001

Data Index: 1161322 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0153. Min Act: -0.0001

Data Index: 195987 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0149. Min Act: -0.0001

Data Index: 768245 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0149. Min Act: -0.0001

Data Index: 250700 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0151. Min Act: -0.0001

Data Index: 1609182 (Python Code)

Max Activating Token Index: 32

Text #11

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0149. Min Act: -0.0001

Data Index: 396494 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0149. Min Act: -0.0001

Data Index: 67837 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0147. Min Act: -0.0001

Data Index: 1199512 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0147. Min Act: -0.0001

Data Index: 786138 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0146. Min Act: -0.0001

Data Index: 621453 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0146. Min Act: -0.0001

Data Index: 1465140 (Python Code)

Max Activating Token Index: 63

Text #17

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0144. Min Act: -0.0001

Data Index: 1015180 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0145. Min Act: -0.0001

Data Index: 1305931 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0144. Min Act: -0.0001

Data Index: 861532 (C4 (Web Text))

Max Activating Token Index: 458