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

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

Neuron 4802 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0943. Min Range: -1.0943

Max Act: 1.0943. Min Act: -0.0000

Data Index: 227277 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.9996. Min Act: -0.0000

Data Index: 1152961 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.8022. Min Act: -0.0000

Data Index: 1128426 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6978. Min Act: -0.0000

Data Index: 658523 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6936. Min Act: -0.0000

Data Index: 158065 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.7251. Min Act: -0.0000

Data Index: 292102 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6447. Min Act: -0.0000

Data Index: 650768 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6616. Min Act: -0.0000

Data Index: 1314143 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6293. Min Act: -0.0000

Data Index: 1045695 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6382. Min Act: -0.0000

Data Index: 847254 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6174. Min Act: -0.0000

Data Index: 1266022 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6479. Min Act: -0.0000

Data Index: 854922 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6078. Min Act: -0.0000

Data Index: 1197706 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.5612. Min Act: -0.0000

Data Index: 1064369 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6056. Min Act: -0.0000

Data Index: 91791 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6217. Min Act: -0.0000

Data Index: 783682 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6201. Min Act: -0.0000

Data Index: 356298 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6159. Min Act: -0.0000

Data Index: 1027069 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.5758. Min Act: -0.0000

Data Index: 1285480 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 1.0943. Min Range: -1.0943

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1172235 (C4 (Web Text))

Max Activating Token Index: 639