Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1642 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.3701. Min Act: -0.0001

Data Index: 794379 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.3284. Min Act: -0.0001

Data Index: 36136 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.3134. Min Act: -0.0001

Data Index: 343813 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.3281. Min Act: -0.0001

Data Index: 417778 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.3228. Min Act: -0.0001

Data Index: 433687 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.3094. Min Act: -0.0001

Data Index: 638663 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.3018. Min Act: -0.0001

Data Index: 1358272 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.3089. Min Act: -0.0001

Data Index: 740460 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.2783. Min Act: -0.0001

Data Index: 390657 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.3095. Min Act: -0.0001

Data Index: 1270431 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.2893. Min Act: -0.0001

Data Index: 344298 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.3071. Min Act: -0.0001

Data Index: 365884 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.2910. Min Act: -0.0001

Data Index: 756654 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.3046. Min Act: -0.0001

Data Index: 190364 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.2941. Min Act: -0.0001

Data Index: 1214920 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.2813. Min Act: -0.0001

Data Index: 784331 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.3100. Min Act: -0.0001

Data Index: 1161740 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.3013. Min Act: -0.0001

Data Index: 1098889 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.2747. Min Act: -0.0001

Data Index: 854281 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.3701. Min Range: -0.3701

Max Act: 0.2835. Min Act: -0.0001

Data Index: 504897 (C4 (Web Text))

Max Activating Token Index: 345