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

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

Neuron 4294 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3052. Min Range: -4.3052

Max Act: 4.3052. Min Act: -0.0000

Data Index: 1136331 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 4.3052. Min Range: -4.3052

Max Act: 3.6839. Min Act: -0.0000

Data Index: 435783 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 4.3052. Min Range: -4.3052

Max Act: 3.7530. Min Act: -0.0000

Data Index: 1156343 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 4.3052. Min Range: -4.3052

Max Act: 3.5609. Min Act: -0.0000

Data Index: 386916 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 4.3052. Min Range: -4.3052

Max Act: 3.3633. Min Act: -0.0000

Data Index: 194729 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 4.3052. Min Range: -4.3052

Max Act: 3.2452. Min Act: -0.0000

Data Index: 184396 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 4.3052. Min Range: -4.3052

Max Act: 3.0888. Min Act: -0.0000

Data Index: 19839 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 4.3052. Min Range: -4.3052

Max Act: 2.6642. Min Act: -0.0000

Data Index: 58026 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 4.3052. Min Range: -4.3052

Max Act: 2.9170. Min Act: -0.0000

Data Index: 1319484 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 4.3052. Min Range: -4.3052

Max Act: 2.8560. Min Act: -0.0000

Data Index: 936913 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 4.3052. Min Range: -4.3052

Max Act: 2.5613. Min Act: -0.0000

Data Index: 1311020 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 4.3052. Min Range: -4.3052

Max Act: 2.8073. Min Act: -0.0000

Data Index: 391161 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 4.3052. Min Range: -4.3052

Max Act: 2.5126. Min Act: -0.0000

Data Index: 486546 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 4.3052. Min Range: -4.3052

Max Act: 2.6972. Min Act: -0.0000

Data Index: 633324 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 4.3052. Min Range: -4.3052

Max Act: 2.8505. Min Act: 0.0000

Data Index: 1196477 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 4.3052. Min Range: -4.3052

Max Act: 2.5510. Min Act: -0.0000

Data Index: 1069302 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 4.3052. Min Range: -4.3052

Max Act: 2.1711. Min Act: -0.0000

Data Index: 1167912 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 4.3052. Min Range: -4.3052

Max Act: 2.5403. Min Act: -0.0000

Data Index: 218317 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 4.3052. Min Range: -4.3052

Max Act: 2.6180. Min Act: -0.0000

Data Index: 251029 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 4.3052. Min Range: -4.3052

Max Act: 2.3345. Min Act: -0.0000

Data Index: 539633 (C4 (Web Text))

Max Activating Token Index: 840