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

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

Neuron 5032 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0799. Min Range: -3.0799

Max Act: 3.0089. Min Act: -0.0000

Data Index: 1524808 (Python Code)

Max Activating Token Index: 168

Text #1

Max Range: 3.0799. Min Range: -3.0799

Max Act: 2.9821. Min Act: -0.0000

Data Index: 1526317 (Python Code)

Max Activating Token Index: 584

Text #2

Max Range: 3.0799. Min Range: -3.0799

Max Act: 3.0799. Min Act: -0.0000

Data Index: 1138929 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 3.0799. Min Range: -3.0799

Max Act: 2.7983. Min Act: -0.0000

Data Index: 1580455 (Python Code)

Max Activating Token Index: 116

Text #4

Max Range: 3.0799. Min Range: -3.0799

Max Act: 2.9887. Min Act: -0.0000

Data Index: 1448763 (Python Code)

Max Activating Token Index: 400

Text #5

Max Range: 3.0799. Min Range: -3.0799

Max Act: 2.8657. Min Act: -0.0000

Data Index: 1539327 (Python Code)

Max Activating Token Index: 529

Text #6

Max Range: 3.0799. Min Range: -3.0799

Max Act: 2.8849. Min Act: -0.0000

Data Index: 489809 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 3.0799. Min Range: -3.0799

Max Act: 2.6551. Min Act: -0.0000

Data Index: 1457200 (Python Code)

Max Activating Token Index: 795

Text #8

Max Range: 3.0799. Min Range: -3.0799

Max Act: 2.7438. Min Act: -0.0000

Data Index: 1553560 (Python Code)

Max Activating Token Index: 345

Text #9

Max Range: 3.0799. Min Range: -3.0799

Max Act: 2.8514. Min Act: -0.0000

Data Index: 1367386 (Python Code)

Max Activating Token Index: 441

Text #10

Max Range: 3.0799. Min Range: -3.0799

Max Act: 2.4388. Min Act: -0.0000

Data Index: 1562824 (Python Code)

Max Activating Token Index: 303

Text #11

Max Range: 3.0799. Min Range: -3.0799

Max Act: 2.5574. Min Act: -0.0000

Data Index: 1410347 (Python Code)

Max Activating Token Index: 67

Text #12

Max Range: 3.0799. Min Range: -3.0799

Max Act: 2.6612. Min Act: -0.0000

Data Index: 1384635 (Python Code)

Max Activating Token Index: 71

Text #13

Max Range: 3.0799. Min Range: -3.0799

Max Act: 2.6077. Min Act: -0.0000

Data Index: 1374441 (Python Code)

Max Activating Token Index: 41

Text #14

Max Range: 3.0799. Min Range: -3.0799

Max Act: 2.3473. Min Act: -0.0000

Data Index: 1377206 (Python Code)

Max Activating Token Index: 206

Text #15

Max Range: 3.0799. Min Range: -3.0799

Max Act: 2.3381. Min Act: -0.0000

Data Index: 1616291 (Python Code)

Max Activating Token Index: 176

Text #16

Max Range: 3.0799. Min Range: -3.0799

Max Act: 2.5829. Min Act: -0.0000

Data Index: 1542798 (Python Code)

Max Activating Token Index: 461

Text #17

Max Range: 3.0799. Min Range: -3.0799

Max Act: 2.6545. Min Act: -0.0000

Data Index: 961878 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 3.0799. Min Range: -3.0799

Max Act: 2.0532. Min Act: -0.0000

Data Index: 1552043 (Python Code)

Max Activating Token Index: 967

Text #19

Max Range: 3.0799. Min Range: -3.0799

Max Act: 2.4209. Min Act: -0.0000

Data Index: 1056033 (C4 (Web Text))

Max Activating Token Index: 604