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

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

Neuron 3187 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: 0.7847. Min Range: -0.7847

Max Act: 0.7847. Min Act: -0.0000

Data Index: 386576 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.7826. Min Act: -0.0000

Data Index: 820158 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.7063. Min Act: -0.0000

Data Index: 558870 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6491. Min Act: -0.0000

Data Index: 403945 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.7256. Min Act: -0.0000

Data Index: 760143 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6865. Min Act: -0.0000

Data Index: 18552 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6533. Min Act: -0.0000

Data Index: 1234532 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6413. Min Act: -0.0000

Data Index: 806079 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1064080 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6465. Min Act: -0.0000

Data Index: 430404 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5894. Min Act: -0.0000

Data Index: 88771 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5941. Min Act: -0.0000

Data Index: 188706 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6130. Min Act: -0.0000

Data Index: 944878 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6211. Min Act: -0.0000

Data Index: 90247 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6162. Min Act: -0.0000

Data Index: 539448 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5596. Min Act: -0.0000

Data Index: 132346 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6494. Min Act: -0.0000

Data Index: 980521 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5655. Min Act: -0.0000

Data Index: 969859 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6043. Min Act: -0.0000

Data Index: 997765 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6114. Min Act: -0.0000

Data Index: 63141 (C4 (Web Text))

Max Activating Token Index: 270