Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3663 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9565. Min Range: -0.9565

Max Act: 0.9024. Min Act: -0.0000

Data Index: 981897 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 0.9565. Min Range: -0.9565

Max Act: 0.8676. Min Act: 0.0004

Data Index: 810947 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.9565. Min Range: -0.9565

Max Act: 0.9565. Min Act: 0.0000

Data Index: 105483 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.9565. Min Range: -0.9565

Max Act: 0.8548. Min Act: -0.0000

Data Index: 162864 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 0.9565. Min Range: -0.9565

Max Act: 0.8468. Min Act: -0.0000

Data Index: 570837 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.9565. Min Range: -0.9565

Max Act: 0.8703. Min Act: -0.0000

Data Index: 99450 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.9565. Min Range: -0.9565

Max Act: 0.8682. Min Act: -0.0000

Data Index: 94940 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.9565. Min Range: -0.9565

Max Act: 0.8220. Min Act: -0.0000

Data Index: 997027 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.9565. Min Range: -0.9565

Max Act: 0.7993. Min Act: -0.0000

Data Index: 347035 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.9565. Min Range: -0.9565

Max Act: 0.8240. Min Act: -0.0000

Data Index: 549570 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 0.9565. Min Range: -0.9565

Max Act: 0.7666. Min Act: -0.0000

Data Index: 92450 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.9565. Min Range: -0.9565

Max Act: 0.8416. Min Act: -0.0000

Data Index: 648285 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.9565. Min Range: -0.9565

Max Act: 0.8200. Min Act: -0.0000

Data Index: 550180 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.9565. Min Range: -0.9565

Max Act: 0.8306. Min Act: -0.0000

Data Index: 58609 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.9565. Min Range: -0.9565

Max Act: 0.8013. Min Act: -0.0000

Data Index: 417483 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.9565. Min Range: -0.9565

Max Act: 0.8156. Min Act: -0.0000

Data Index: 658040 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 0.9565. Min Range: -0.9565

Max Act: 0.7616. Min Act: -0.0000

Data Index: 237025 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.9565. Min Range: -0.9565

Max Act: 0.7581. Min Act: -0.0000

Data Index: 936669 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.9565. Min Range: -0.9565

Max Act: 0.8547. Min Act: -0.0000

Data Index: 1299378 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.9565. Min Range: -0.9565

Max Act: 0.6937. Min Act: -0.0000

Data Index: 963899 (C4 (Web Text))

Max Activating Token Index: 733