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

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

Neuron 1808 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: 0.0160. Min Range: -0.0160

Max Act: 0.0160. Min Act: -0.0002

Data Index: 884299 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0155. Min Act: -0.0001

Data Index: 931950 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0156. Min Act: -0.0001

Data Index: 1003969 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0154. Min Act: -0.0001

Data Index: 903802 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0153. Min Act: -0.0001

Data Index: 681980 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0152. Min Act: -0.0001

Data Index: 710092 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0151. Min Act: -0.0001

Data Index: 936901 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0152. Min Act: -0.0001

Data Index: 1310762 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0152. Min Act: -0.0001

Data Index: 1016881 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0147. Min Act: -0.0001

Data Index: 1141372 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0145. Min Act: -0.0001

Data Index: 533383 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0147. Min Act: -0.0001

Data Index: 1007492 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0147. Min Act: -0.0001

Data Index: 856648 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0146. Min Act: -0.0001

Data Index: 4415 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0143. Min Act: -0.0001

Data Index: 703878 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0145. Min Act: -0.0001

Data Index: 398532 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0144. Min Act: -0.0001

Data Index: 520382 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0145. Min Act: -0.0001

Data Index: 1171303 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0143. Min Act: -0.0002

Data Index: 49458 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0146. Min Act: -0.0001

Data Index: 843349 (C4 (Web Text))

Max Activating Token Index: 950