Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 123 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0064. Min Act: -0.0005

Data Index: 476340 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0062. Min Act: -0.0005

Data Index: 715666 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0061. Min Act: -0.0005

Data Index: 567999 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0059. Min Act: -0.0005

Data Index: 491546 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0059. Min Act: -0.0005

Data Index: 442561 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0059. Min Act: -0.0005

Data Index: 992540 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0058. Min Act: -0.0005

Data Index: 981820 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0058. Min Act: -0.0005

Data Index: 699785 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0058. Min Act: -0.0005

Data Index: 360279 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0056. Min Act: -0.0005

Data Index: 717867 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0057. Min Act: -0.0004

Data Index: 1460506 (Python Code)

Max Activating Token Index: 116

Text #11

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0056. Min Act: -0.0005

Data Index: 1401513 (Python Code)

Max Activating Token Index: 570

Text #12

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0056. Min Act: -0.0005

Data Index: 680549 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0056. Min Act: -0.0005

Data Index: 841208 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0055. Min Act: -0.0005

Data Index: 788297 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0055. Min Act: -0.0005

Data Index: 1173787 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0055. Min Act: -0.0005

Data Index: 1393332 (Python Code)

Max Activating Token Index: 625

Text #17

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0054. Min Act: -0.0005

Data Index: 193864 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0055. Min Act: -0.0005

Data Index: 1153219 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0054. Min Act: -0.0005

Data Index: 576636 (C4 (Web Text))

Max Activating Token Index: 480