Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3639 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1837. Min Range: -1.1837

Max Act: 1.1837. Min Act: -0.0001

Data Index: 92717 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.9489. Min Act: -0.0001

Data Index: 736005 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.9612. Min Act: -0.0001

Data Index: 179832 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.9777. Min Act: -0.0001

Data Index: 1323152 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.9966. Min Act: -0.0001

Data Index: 1144035 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.8490. Min Act: -0.0001

Data Index: 3765 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.8230. Min Act: -0.0001

Data Index: 1085105 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.7600. Min Act: -0.0001

Data Index: 1191958 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.7627. Min Act: -0.0001

Data Index: 48165 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.6435. Min Act: -0.0001

Data Index: 861170 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.7459. Min Act: -0.0001

Data Index: 1059269 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.6710. Min Act: -0.0001

Data Index: 1359106 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.7443. Min Act: -0.0001

Data Index: 644570 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.6796. Min Act: -0.0001

Data Index: 502515 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.7014. Min Act: -0.0001

Data Index: 709517 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.6983. Min Act: -0.0001

Data Index: 505225 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.6479. Min Act: -0.0001

Data Index: 439288 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.6794. Min Act: -0.0001

Data Index: 1035875 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.5808. Min Act: -0.0001

Data Index: 1289449 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.6426. Min Act: -0.0001

Data Index: 504453 (C4 (Web Text))

Max Activating Token Index: 874