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

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

Neuron 3314 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2997. Min Range: -1.2997

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1326680 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 1.2997. Min Range: -1.2997

Max Act: 1.2997. Min Act: -0.0000

Data Index: 1051184 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 1.2997. Min Range: -1.2997

Max Act: 1.0261. Min Act: -0.0000

Data Index: 1002959 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 1.2997. Min Range: -1.2997

Max Act: 1.0722. Min Act: -0.0001

Data Index: 1115426 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 1.2997. Min Range: -1.2997

Max Act: 1.0194. Min Act: -0.0000

Data Index: 426000 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.9646. Min Act: -0.0000

Data Index: 1037222 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8998. Min Act: -0.0001

Data Index: 1280576 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.9667. Min Act: -0.0001

Data Index: 713858 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.9729. Min Act: -0.0000

Data Index: 719608 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.9006. Min Act: -0.0000

Data Index: 967155 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8320. Min Act: -0.0000

Data Index: 715547 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8523. Min Act: -0.0000

Data Index: 1193594 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8285. Min Act: -0.0000

Data Index: 584111 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8476. Min Act: -0.0000

Data Index: 937814 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8030. Min Act: -0.0000

Data Index: 1053232 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8815. Min Act: -0.0000

Data Index: 824167 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8222. Min Act: -0.0000

Data Index: 811633 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1111971 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.7666. Min Act: -0.0000

Data Index: 474950 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.7865. Min Act: -0.0000

Data Index: 1085849 (C4 (Web Text))

Max Activating Token Index: 454