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

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

Neuron 1152 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: 0.9990. Min Range: -0.9990

Max Act: 0.9990. Min Act: -0.0001

Data Index: 241493 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.9990. Min Range: -0.9990

Max Act: 0.9532. Min Act: -0.0001

Data Index: 1409148 (Python Code)

Max Activating Token Index: 542

Text #2

Max Range: 0.9990. Min Range: -0.9990

Max Act: 0.9595. Min Act: -0.0001

Data Index: 1563730 (Python Code)

Max Activating Token Index: 672

Text #3

Max Range: 0.9990. Min Range: -0.9990

Max Act: 0.8458. Min Act: -0.0001

Data Index: 500239 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.9990. Min Range: -0.9990

Max Act: 0.8708. Min Act: -0.0001

Data Index: 765587 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.9990. Min Range: -0.9990

Max Act: 0.8526. Min Act: -0.0001

Data Index: 1396456 (Python Code)

Max Activating Token Index: 24

Text #6

Max Range: 0.9990. Min Range: -0.9990

Max Act: 0.8920. Min Act: -0.0001

Data Index: 973448 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.9990. Min Range: -0.9990

Max Act: 0.9017. Min Act: -0.0001

Data Index: 1388887 (Python Code)

Max Activating Token Index: 589

Text #8

Max Range: 0.9990. Min Range: -0.9990

Max Act: 0.7082. Min Act: -0.0001

Data Index: 1485089 (Python Code)

Max Activating Token Index: 586

Text #9

Max Range: 0.9990. Min Range: -0.9990

Max Act: 0.7865. Min Act: -0.0001

Data Index: 1582837 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 0.9990. Min Range: -0.9990

Max Act: 0.8935. Min Act: -0.0001

Data Index: 1574535 (Python Code)

Max Activating Token Index: 668

Text #11

Max Range: 0.9990. Min Range: -0.9990

Max Act: 0.7855. Min Act: -0.0001

Data Index: 1289371 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 0.9990. Min Range: -0.9990

Max Act: 0.7415. Min Act: -0.0001

Data Index: 1497234 (Python Code)

Max Activating Token Index: 728

Text #13

Max Range: 0.9990. Min Range: -0.9990

Max Act: 0.7902. Min Act: -0.0001

Data Index: 519454 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.9990. Min Range: -0.9990

Max Act: 0.7741. Min Act: -0.0001

Data Index: 1461325 (Python Code)

Max Activating Token Index: 853

Text #15

Max Range: 0.9990. Min Range: -0.9990

Max Act: 0.7002. Min Act: -0.0001

Data Index: 30738 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 0.9990. Min Range: -0.9990

Max Act: 0.8032. Min Act: -0.0001

Data Index: 1163977 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.9990. Min Range: -0.9990

Max Act: 0.7163. Min Act: -0.0001

Data Index: 659856 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 0.9990. Min Range: -0.9990

Max Act: 0.7292. Min Act: -0.0000

Data Index: 913556 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 0.9990. Min Range: -0.9990

Max Act: 0.7699. Min Act: -0.0001

Data Index: 978330 (C4 (Web Text))

Max Activating Token Index: 214