Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3046 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0933. Min Act: -0.0003

Data Index: 1433874 (Python Code)

Max Activating Token Index: 985

Text #1

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0886. Min Act: -0.0003

Data Index: 1451800 (Python Code)

Max Activating Token Index: 976

Text #2

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0758. Min Act: -0.0003

Data Index: 1468395 (Python Code)

Max Activating Token Index: 941

Text #3

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0782. Min Act: -0.0003

Data Index: 1574022 (Python Code)

Max Activating Token Index: 987

Text #4

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0726. Min Act: -0.0003

Data Index: 1644393 (Python Code)

Max Activating Token Index: 880

Text #5

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0641. Min Act: -0.0003

Data Index: 1618178 (Python Code)

Max Activating Token Index: 984

Text #6

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0637. Min Act: -0.0003

Data Index: 1456520 (Python Code)

Max Activating Token Index: 1011

Text #7

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1367300 (Python Code)

Max Activating Token Index: 954

Text #8

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0601. Min Act: -0.0003

Data Index: 1434317 (Python Code)

Max Activating Token Index: 988

Text #9

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0595. Min Act: -0.0003

Data Index: 1043020 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0607. Min Act: -0.0003

Data Index: 1494437 (Python Code)

Max Activating Token Index: 1016

Text #11

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0570. Min Act: -0.0003

Data Index: 1556313 (Python Code)

Max Activating Token Index: 1017

Text #12

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0545. Min Act: -0.0003

Data Index: 1263990 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0499. Min Act: -0.0003

Data Index: 1547227 (Python Code)

Max Activating Token Index: 996

Text #14

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0496. Min Act: -0.0003

Data Index: 1454119 (Python Code)

Max Activating Token Index: 976

Text #15

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1575975 (Python Code)

Max Activating Token Index: 798

Text #16

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1652140 (Python Code)

Max Activating Token Index: 900

Text #17

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1467871 (Python Code)

Max Activating Token Index: 1007

Text #18

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0480. Min Act: -0.0003

Data Index: 1598032 (Python Code)

Max Activating Token Index: 992

Text #19

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1614894 (Python Code)

Max Activating Token Index: 973