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

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

Neuron 3282 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.9519. Min Act: -0.0000

Data Index: 847201 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.9849. Min Act: -0.0001

Data Index: 247253 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8671. Min Act: -0.0000

Data Index: 962052 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8174. Min Act: -0.0001

Data Index: 317240 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8354. Min Act: -0.0001

Data Index: 1123676 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8292. Min Act: -0.0001

Data Index: 822578 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8231. Min Act: -0.0001

Data Index: 633289 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8434. Min Act: -0.0001

Data Index: 8401 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7896. Min Act: -0.0001

Data Index: 526220 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8112. Min Act: -0.0001

Data Index: 108479 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7926. Min Act: -0.0000

Data Index: 816293 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8145. Min Act: -0.0000

Data Index: 265468 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8224. Min Act: -0.0001

Data Index: 1142721 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7779. Min Act: -0.0001

Data Index: 243105 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7401. Min Act: -0.0001

Data Index: 1073822 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7442. Min Act: -0.0001

Data Index: 563666 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7640. Min Act: -0.0001

Data Index: 183915 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7615. Min Act: -0.0001

Data Index: 344766 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7507. Min Act: -0.0001

Data Index: 947243 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7839. Min Act: -0.0001

Data Index: 758116 (C4 (Web Text))

Max Activating Token Index: 653