Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 457 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4663. Min Range: -1.4663

Max Act: 1.4663. Min Act: -0.0000

Data Index: 869873 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.9224. Min Act: -0.0001

Data Index: 60406 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.8527. Min Act: -0.0000

Data Index: 1285717 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.8049. Min Act: -0.0000

Data Index: 328939 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.7712. Min Act: -0.0001

Data Index: 269091 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.7623. Min Act: -0.0000

Data Index: 340904 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.7270. Min Act: -0.0000

Data Index: 1110038 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.7268. Min Act: -0.0000

Data Index: 720023 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.7496. Min Act: -0.0000

Data Index: 1088574 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.7081. Min Act: -0.0000

Data Index: 728864 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.6958. Min Act: -0.0000

Data Index: 1305149 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.6725. Min Act: -0.0000

Data Index: 1194806 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.6910. Min Act: -0.0000

Data Index: 537503 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.6608. Min Act: -0.0000

Data Index: 182989 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.6748. Min Act: -0.0000

Data Index: 377325 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.6515. Min Act: -0.0000

Data Index: 882376 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.6413. Min Act: -0.0001

Data Index: 197702 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.6386. Min Act: -0.0000

Data Index: 298847 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.6505. Min Act: -0.0000

Data Index: 1158199 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 1.4663. Min Range: -1.4663

Max Act: 0.6269. Min Act: -0.0000

Data Index: 395140 (C4 (Web Text))

Max Activating Token Index: 743