Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2171 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0053. Min Range: -1.0053

Max Act: 1.0053. Min Act: -0.0000

Data Index: 1539058 (Python Code)

Max Activating Token Index: 526

Text #1

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.9451. Min Act: -0.0000

Data Index: 1534003 (Python Code)

Max Activating Token Index: 252

Text #2

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.9322. Min Act: -0.0000

Data Index: 997587 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.9285. Min Act: -0.0000

Data Index: 569667 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.9263. Min Act: 0.0000

Data Index: 545397 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8922. Min Act: 0.0001

Data Index: 1434081 (Python Code)

Max Activating Token Index: 699

Text #6

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8326. Min Act: -0.0000

Data Index: 1574147 (Python Code)

Max Activating Token Index: 22

Text #7

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8109. Min Act: -0.0000

Data Index: 1636691 (Python Code)

Max Activating Token Index: 704

Text #8

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8343. Min Act: -0.0000

Data Index: 83356 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8051. Min Act: 0.0001

Data Index: 1415076 (Python Code)

Max Activating Token Index: 985

Text #10

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8061. Min Act: -0.0000

Data Index: 809747 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.6461. Min Act: -0.0000

Data Index: 1615403 (Python Code)

Max Activating Token Index: 897

Text #12

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7184. Min Act: 0.0000

Data Index: 743492 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.6909. Min Act: 0.0000

Data Index: 1439254 (Python Code)

Max Activating Token Index: 145

Text #14

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7079. Min Act: -0.0000

Data Index: 955135 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7178. Min Act: 0.0000

Data Index: 1490684 (Python Code)

Max Activating Token Index: 56

Text #16

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7683. Min Act: -0.0000

Data Index: 825446 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.6978. Min Act: -0.0000

Data Index: 1283822 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7050. Min Act: -0.0000

Data Index: 1410161 (Python Code)

Max Activating Token Index: 1022

Text #19

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.6723. Min Act: 0.0001

Data Index: 1511216 (Python Code)

Max Activating Token Index: 231