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

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

Neuron 2707 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1361. Min Act: -0.0001

Data Index: 656931 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1272. Min Act: -0.0001

Data Index: 192141 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1226. Min Act: -0.0001

Data Index: 985919 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1153. Min Act: -0.0001

Data Index: 732341 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1103. Min Act: -0.0001

Data Index: 1053610 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1145. Min Act: -0.0001

Data Index: 503171 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0977. Min Act: -0.0001

Data Index: 436160 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1062. Min Act: -0.0001

Data Index: 439329 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1283752 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0992. Min Act: -0.0001

Data Index: 401064 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1056. Min Act: -0.0001

Data Index: 766183 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1011. Min Act: -0.0001

Data Index: 29005 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1014. Min Act: -0.0001

Data Index: 1144935 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0893. Min Act: -0.0001

Data Index: 183286 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1001. Min Act: -0.0001

Data Index: 69441 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1056. Min Act: -0.0001

Data Index: 62686 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0936. Min Act: -0.0001

Data Index: 326132 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0953. Min Act: -0.0001

Data Index: 32627 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0979. Min Act: -0.0001

Data Index: 73118 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0941. Min Act: -0.0001

Data Index: 1083004 (C4 (Web Text))

Max Activating Token Index: 755