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

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

Neuron 1070 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4608. Min Range: -2.4608

Max Act: 2.4608. Min Act: -0.0000

Data Index: 1216918 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 2.4608. Min Range: -2.4608

Max Act: 2.0496. Min Act: -0.0000

Data Index: 101639 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 2.4608. Min Range: -2.4608

Max Act: 2.0534. Min Act: -0.0000

Data Index: 769137 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 2.4608. Min Range: -2.4608

Max Act: 2.1402. Min Act: -0.0000

Data Index: 147954 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 2.4608. Min Range: -2.4608

Max Act: 2.0095. Min Act: -0.0000

Data Index: 1230838 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 2.4608. Min Range: -2.4608

Max Act: 2.1137. Min Act: -0.0000

Data Index: 1280583 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 2.4608. Min Range: -2.4608

Max Act: 2.0983. Min Act: -0.0000

Data Index: 972832 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 2.4608. Min Range: -2.4608

Max Act: 2.0032. Min Act: -0.0000

Data Index: 790143 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 2.4608. Min Range: -2.4608

Max Act: 1.9834. Min Act: -0.0000

Data Index: 1049753 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 2.4608. Min Range: -2.4608

Max Act: 2.0664. Min Act: -0.0000

Data Index: 267409 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 2.4608. Min Range: -2.4608

Max Act: 2.0475. Min Act: -0.0000

Data Index: 1333477 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 2.4608. Min Range: -2.4608

Max Act: 2.0260. Min Act: -0.0000

Data Index: 227371 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 2.4608. Min Range: -2.4608

Max Act: 2.0187. Min Act: -0.0000

Data Index: 374171 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 2.4608. Min Range: -2.4608

Max Act: 1.9969. Min Act: -0.0000

Data Index: 372392 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 2.4608. Min Range: -2.4608

Max Act: 2.0068. Min Act: -0.0000

Data Index: 644313 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 2.4608. Min Range: -2.4608

Max Act: 1.9712. Min Act: -0.0000

Data Index: 972257 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 2.4608. Min Range: -2.4608

Max Act: 1.9730. Min Act: -0.0000

Data Index: 612749 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 2.4608. Min Range: -2.4608

Max Act: 1.9366. Min Act: -0.0000

Data Index: 1243149 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 2.4608. Min Range: -2.4608

Max Act: 1.7326. Min Act: -0.0000

Data Index: 279780 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 2.4608. Min Range: -2.4608

Max Act: 1.9142. Min Act: -0.0000

Data Index: 1242756 (C4 (Web Text))

Max Activating Token Index: 993