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

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

Neuron 5995 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0920. Min Range: -1.0920

Max Act: 1.0920. Min Act: -0.0000

Data Index: 8105 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.9409. Min Act: -0.0000

Data Index: 323820 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.8777. Min Act: -0.0000

Data Index: 238118 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.8109. Min Act: -0.0000

Data Index: 1137374 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.8201. Min Act: -0.0000

Data Index: 2550 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.8605. Min Act: -0.0000

Data Index: 903261 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.7663. Min Act: -0.0000

Data Index: 933610 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.7850. Min Act: -0.0000

Data Index: 833880 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1189889 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.7005. Min Act: -0.0000

Data Index: 767989 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.6991. Min Act: -0.0000

Data Index: 621760 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1139211 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.6794. Min Act: -0.0000

Data Index: 744933 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.6757. Min Act: -0.0000

Data Index: 720779 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.6606. Min Act: -0.0000

Data Index: 294248 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.6883. Min Act: -0.0000

Data Index: 1093684 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.6601. Min Act: -0.0000

Data Index: 987959 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.7063. Min Act: -0.0000

Data Index: 127664 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.6765. Min Act: -0.0000

Data Index: 308065 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 1.0920. Min Range: -1.0920

Max Act: 0.6926. Min Act: -0.0000

Data Index: 363110 (C4 (Web Text))

Max Activating Token Index: 844