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

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

Neuron 2349 in Layer 1

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: 1.2022. Min Range: -1.2022

Max Act: 1.2022. Min Act: -0.0002

Data Index: 283466 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 1.2022. Min Range: -1.2022

Max Act: 1.0667. Min Act: -0.0002

Data Index: 187506 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 1.2022. Min Range: -1.2022

Max Act: 1.0913. Min Act: -0.0002

Data Index: 751734 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 1.2022. Min Range: -1.2022

Max Act: 1.0899. Min Act: -0.0003

Data Index: 651997 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 1.2022. Min Range: -1.2022

Max Act: 1.0547. Min Act: -0.0002

Data Index: 836343 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 1.2022. Min Range: -1.2022

Max Act: 1.0619. Min Act: -0.0002

Data Index: 1351814 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 1.2022. Min Range: -1.2022

Max Act: 1.0578. Min Act: -0.0002

Data Index: 978152 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 1.2022. Min Range: -1.2022

Max Act: 1.0194. Min Act: -0.0003

Data Index: 554567 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 1.2022. Min Range: -1.2022

Max Act: 1.0204. Min Act: -0.0002

Data Index: 1213148 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 1.2022. Min Range: -1.2022

Max Act: 1.0153. Min Act: -0.0002

Data Index: 545978 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 1.2022. Min Range: -1.2022

Max Act: 1.0182. Min Act: -0.0002

Data Index: 1056466 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 1.2022. Min Range: -1.2022

Max Act: 1.0010. Min Act: -0.0002

Data Index: 321348 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 1.2022. Min Range: -1.2022

Max Act: 0.9858. Min Act: -0.0002

Data Index: 930823 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 1.2022. Min Range: -1.2022

Max Act: 0.9616. Min Act: -0.0002

Data Index: 645209 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 1.2022. Min Range: -1.2022

Max Act: 0.9961. Min Act: -0.0002

Data Index: 285534 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 1.2022. Min Range: -1.2022

Max Act: 0.9678. Min Act: -0.0002

Data Index: 1179106 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 1.2022. Min Range: -1.2022

Max Act: 0.9555. Min Act: -0.0002

Data Index: 567004 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 1.2022. Min Range: -1.2022

Max Act: 0.9808. Min Act: -0.0002

Data Index: 1015119 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 1.2022. Min Range: -1.2022

Max Act: 0.9526. Min Act: -0.0002

Data Index: 254438 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 1.2022. Min Range: -1.2022

Max Act: 0.9398. Min Act: -0.0003

Data Index: 1253325 (C4 (Web Text))

Max Activating Token Index: 243