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

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

Neuron 3682 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: 1.2941. Min Range: -1.2941

Max Act: 1.2941. Min Act: -0.0003

Data Index: 354014 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2340. Min Act: -0.0002

Data Index: 156947 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.1755. Min Act: -0.0002

Data Index: 265067 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.1429. Min Act: -0.0002

Data Index: 70544 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.1356. Min Act: -0.0002

Data Index: 40621 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.1357. Min Act: -0.0002

Data Index: 761135 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.1235. Min Act: -0.0002

Data Index: 1151249 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.1109. Min Act: -0.0002

Data Index: 573287 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.1118. Min Act: -0.0002

Data Index: 1164462 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.1101. Min Act: -0.0002

Data Index: 86374 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.1038. Min Act: -0.0002

Data Index: 227744 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.1004. Min Act: -0.0002

Data Index: 73825 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.0937. Min Act: -0.0002

Data Index: 229694 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.0804. Min Act: -0.0002

Data Index: 105919 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.1089. Min Act: -0.0002

Data Index: 988848 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.0940. Min Act: -0.0002

Data Index: 284126 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.0893. Min Act: -0.0002

Data Index: 826408 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.0810. Min Act: -0.0002

Data Index: 1311178 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.0667. Min Act: -0.0002

Data Index: 412225 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.0817. Min Act: -0.0003

Data Index: 322211 (C4 (Web Text))

Max Activating Token Index: 833