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

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

Neuron 877 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1413. Min Range: -1.1413

Max Act: 1.1144. Min Act: -0.0000

Data Index: 783809 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 1.1413. Min Range: -1.1413

Max Act: 1.1413. Min Act: 0.0000

Data Index: 841541 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 1.1413. Min Range: -1.1413

Max Act: 1.0111. Min Act: 0.0000

Data Index: 1183108 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 1.1413. Min Range: -1.1413

Max Act: 1.0642. Min Act: -0.0000

Data Index: 831409 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 1.1413. Min Range: -1.1413

Max Act: 1.0440. Min Act: -0.0000

Data Index: 360981 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 1.1413. Min Range: -1.1413

Max Act: 1.0221. Min Act: -0.0000

Data Index: 745761 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 1.1413. Min Range: -1.1413

Max Act: 1.0810. Min Act: -0.0000

Data Index: 544896 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.9467. Min Act: 0.0000

Data Index: 1258447 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.9341. Min Act: -0.0000

Data Index: 247444 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.9496. Min Act: -0.0000

Data Index: 349353 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 1.1413. Min Range: -1.1413

Max Act: 1.0035. Min Act: -0.0000

Data Index: 693517 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.9476. Min Act: -0.0000

Data Index: 774843 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.9411. Min Act: -0.0000

Data Index: 1176315 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.9862. Min Act: 0.0000

Data Index: 498137 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.9870. Min Act: -0.0000

Data Index: 308770 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.9208. Min Act: -0.0000

Data Index: 1276371 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.8643. Min Act: -0.0000

Data Index: 952358 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.8636. Min Act: -0.0000

Data Index: 713928 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.8514. Min Act: -0.0000

Data Index: 1240625 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 1.1413. Min Range: -1.1413

Max Act: 0.9059. Min Act: 0.0001

Data Index: 1168097 (C4 (Web Text))

Max Activating Token Index: 579