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

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

Neuron 4542 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3617. Min Range: -3.3617

Max Act: 3.3617. Min Act: -0.0000

Data Index: 1126378 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 3.3617. Min Range: -3.3617

Max Act: 3.0464. Min Act: -0.0000

Data Index: 917937 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.6599. Min Act: -0.0000

Data Index: 363943 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.6211. Min Act: -0.0000

Data Index: 785199 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.5441. Min Act: -0.0000

Data Index: 213331 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.2436. Min Act: -0.0000

Data Index: 549792 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.3403. Min Act: -0.0000

Data Index: 991457 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.2737. Min Act: -0.0000

Data Index: 1264898 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.3068. Min Act: -0.0000

Data Index: 1011823 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.1961. Min Act: -0.0000

Data Index: 793878 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.1787. Min Act: -0.0000

Data Index: 418314 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.1739. Min Act: -0.0000

Data Index: 953515 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.2645. Min Act: -0.0000

Data Index: 1160876 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.3703. Min Act: -0.0000

Data Index: 129275 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.0632. Min Act: -0.0000

Data Index: 224179 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.1740. Min Act: -0.0000

Data Index: 1210794 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.1527. Min Act: -0.0000

Data Index: 187211 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.0044. Min Act: -0.0000

Data Index: 401727 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 3.3617. Min Range: -3.3617

Max Act: 1.9684. Min Act: -0.0000

Data Index: 1219448 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 3.3617. Min Range: -3.3617

Max Act: 2.0841. Min Act: -0.0000

Data Index: 442041 (C4 (Web Text))

Max Activating Token Index: 176