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

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

Neuron 4626 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: 0.0163. Min Range: -0.0163

Max Act: 0.0163. Min Act: -0.0001

Data Index: 457538 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0156. Min Act: -0.0001

Data Index: 1648151 (Python Code)

Max Activating Token Index: 84

Text #2

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0152. Min Act: -0.0001

Data Index: 1511423 (Python Code)

Max Activating Token Index: 89

Text #3

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0154. Min Act: -0.0001

Data Index: 1158802 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0153. Min Act: -0.0001

Data Index: 326771 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0152. Min Act: -0.0001

Data Index: 259210 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0151. Min Act: -0.0001

Data Index: 1185970 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0151. Min Act: -0.0001

Data Index: 22421 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0148. Min Act: -0.0001

Data Index: 1000954 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0148. Min Act: -0.0001

Data Index: 1597039 (Python Code)

Max Activating Token Index: 839

Text #10

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0147. Min Act: -0.0001

Data Index: 1157233 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0145. Min Act: -0.0001

Data Index: 462321 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0148. Min Act: -0.0001

Data Index: 329524 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0148. Min Act: -0.0001

Data Index: 669487 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0146. Min Act: -0.0001

Data Index: 463798 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0144. Min Act: -0.0001

Data Index: 269504 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0146. Min Act: -0.0001

Data Index: 1337350 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0145. Min Act: -0.0001

Data Index: 766275 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0147. Min Act: -0.0001

Data Index: 436078 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0144. Min Act: -0.0001

Data Index: 868148 (C4 (Web Text))

Max Activating Token Index: 31