Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4435 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 6.4993. Min Range: -6.4993

Max Act: 6.4993. Min Act: -0.0000

Data Index: 1324262 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 6.4993. Min Range: -6.4993

Max Act: 5.4018. Min Act: -0.0000

Data Index: 1250793 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 6.4993. Min Range: -6.4993

Max Act: 5.6119. Min Act: -0.0000

Data Index: 904850 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 6.4993. Min Range: -6.4993

Max Act: 5.6191. Min Act: -0.0000

Data Index: 1094062 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 6.4993. Min Range: -6.4993

Max Act: 5.7892. Min Act: -0.0000

Data Index: 91719 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 6.4993. Min Range: -6.4993

Max Act: 5.0878. Min Act: -0.0000

Data Index: 195244 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 6.4993. Min Range: -6.4993

Max Act: 5.4132. Min Act: -0.0000

Data Index: 300927 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 6.4993. Min Range: -6.4993

Max Act: 4.7523. Min Act: -0.0000

Data Index: 1314293 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 6.4993. Min Range: -6.4993

Max Act: 4.8812. Min Act: -0.0000

Data Index: 487532 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 6.4993. Min Range: -6.4993

Max Act: 4.6935. Min Act: -0.0000

Data Index: 98258 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 6.4993. Min Range: -6.4993

Max Act: 4.7897. Min Act: -0.0000

Data Index: 113669 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 6.4993. Min Range: -6.4993

Max Act: 4.5577. Min Act: -0.0000

Data Index: 646322 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 6.4993. Min Range: -6.4993

Max Act: 4.6000. Min Act: -0.0000

Data Index: 26303 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 6.4993. Min Range: -6.4993

Max Act: 4.4326. Min Act: -0.0000

Data Index: 456882 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 6.4993. Min Range: -6.4993

Max Act: 4.9219. Min Act: -0.0000

Data Index: 1196128 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 6.4993. Min Range: -6.4993

Max Act: 4.6830. Min Act: -0.0000

Data Index: 740643 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 6.4993. Min Range: -6.4993

Max Act: 4.6767. Min Act: -0.0000

Data Index: 200508 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 6.4993. Min Range: -6.4993

Max Act: 4.6776. Min Act: -0.0000

Data Index: 1141073 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 6.4993. Min Range: -6.4993

Max Act: 4.8354. Min Act: -0.0000

Data Index: 538373 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 6.4993. Min Range: -6.4993

Max Act: 4.6195. Min Act: -0.0000

Data Index: 1008854 (C4 (Web Text))

Max Activating Token Index: 114