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

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

Neuron 1568 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: 0.9866. Min Range: -0.9866

Max Act: 0.9866. Min Act: -0.0000

Data Index: 1081373 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 0.9866. Min Range: -0.9866

Max Act: 0.9415. Min Act: -0.0000

Data Index: 779148 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.9866. Min Range: -0.9866

Max Act: 0.8557. Min Act: -0.0000

Data Index: 176856 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.9866. Min Range: -0.9866

Max Act: 0.9073. Min Act: -0.0000

Data Index: 1486237 (Python Code)

Max Activating Token Index: 136

Text #4

Max Range: 0.9866. Min Range: -0.9866

Max Act: 0.8871. Min Act: -0.0000

Data Index: 224688 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 0.9866. Min Range: -0.9866

Max Act: 0.8678. Min Act: -0.0000

Data Index: 481500 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.9866. Min Range: -0.9866

Max Act: 0.8866. Min Act: -0.0000

Data Index: 1616924 (Python Code)

Max Activating Token Index: 810

Text #7

Max Range: 0.9866. Min Range: -0.9866

Max Act: 0.8762. Min Act: -0.0000

Data Index: 1524197 (Python Code)

Max Activating Token Index: 690

Text #8

Max Range: 0.9866. Min Range: -0.9866

Max Act: 0.8404. Min Act: -0.0000

Data Index: 541074 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.9866. Min Range: -0.9866

Max Act: 0.8420. Min Act: -0.0000

Data Index: 16640 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 0.9866. Min Range: -0.9866

Max Act: 0.8456. Min Act: -0.0000

Data Index: 1643720 (Python Code)

Max Activating Token Index: 218

Text #11

Max Range: 0.9866. Min Range: -0.9866

Max Act: 0.7962. Min Act: -0.0000

Data Index: 592928 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 0.9866. Min Range: -0.9866

Max Act: 0.8366. Min Act: -0.0000

Data Index: 1275661 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.9866. Min Range: -0.9866

Max Act: 0.8340. Min Act: -0.0000

Data Index: 135142 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.9866. Min Range: -0.9866

Max Act: 0.8544. Min Act: -0.0000

Data Index: 1456279 (Python Code)

Max Activating Token Index: 121

Text #15

Max Range: 0.9866. Min Range: -0.9866

Max Act: 0.8522. Min Act: -0.0000

Data Index: 405415 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.9866. Min Range: -0.9866

Max Act: 0.8703. Min Act: -0.0000

Data Index: 624871 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.9866. Min Range: -0.9866

Max Act: 0.7768. Min Act: -0.0000

Data Index: 825012 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.9866. Min Range: -0.9866

Max Act: 0.8058. Min Act: -0.0000

Data Index: 1399459 (Python Code)

Max Activating Token Index: 1016

Text #19

Max Range: 0.9866. Min Range: -0.9866

Max Act: 0.7832. Min Act: -0.0000

Data Index: 265315 (C4 (Web Text))

Max Activating Token Index: 870