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

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

Neuron 5413 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1445. Min Range: -4.1445

Max Act: 4.1445. Min Act: -0.0000

Data Index: 1581734 (Python Code)

Max Activating Token Index: 981

Text #1

Max Range: 4.1445. Min Range: -4.1445

Max Act: 4.0687. Min Act: -0.0000

Data Index: 1542435 (Python Code)

Max Activating Token Index: 648

Text #2

Max Range: 4.1445. Min Range: -4.1445

Max Act: 3.5114. Min Act: -0.0000

Data Index: 1523049 (Python Code)

Max Activating Token Index: 1002

Text #3

Max Range: 4.1445. Min Range: -4.1445

Max Act: 3.2564. Min Act: -0.0000

Data Index: 1383693 (Python Code)

Max Activating Token Index: 780

Text #4

Max Range: 4.1445. Min Range: -4.1445

Max Act: 2.7404. Min Act: -0.0000

Data Index: 1450288 (Python Code)

Max Activating Token Index: 632

Text #5

Max Range: 4.1445. Min Range: -4.1445

Max Act: 2.6586. Min Act: -0.0000

Data Index: 1533043 (Python Code)

Max Activating Token Index: 888

Text #6

Max Range: 4.1445. Min Range: -4.1445

Max Act: 2.7104. Min Act: -0.0000

Data Index: 1507801 (Python Code)

Max Activating Token Index: 693

Text #7

Max Range: 4.1445. Min Range: -4.1445

Max Act: 2.6273. Min Act: -0.0000

Data Index: 1543193 (Python Code)

Max Activating Token Index: 96

Text #8

Max Range: 4.1445. Min Range: -4.1445

Max Act: 2.3734. Min Act: -0.0000

Data Index: 1578398 (Python Code)

Max Activating Token Index: 138

Text #9

Max Range: 4.1445. Min Range: -4.1445

Max Act: 2.1136. Min Act: -0.0000

Data Index: 1515984 (Python Code)

Max Activating Token Index: 861

Text #10

Max Range: 4.1445. Min Range: -4.1445

Max Act: 2.2003. Min Act: -0.0000

Data Index: 1375288 (Python Code)

Max Activating Token Index: 341

Text #11

Max Range: 4.1445. Min Range: -4.1445

Max Act: 2.0684. Min Act: -0.0000

Data Index: 1586538 (Python Code)

Max Activating Token Index: 748

Text #12

Max Range: 4.1445. Min Range: -4.1445

Max Act: 2.1465. Min Act: -0.0000

Data Index: 1370719 (Python Code)

Max Activating Token Index: 367

Text #13

Max Range: 4.1445. Min Range: -4.1445

Max Act: 1.8291. Min Act: -0.0000

Data Index: 1603497 (Python Code)

Max Activating Token Index: 436

Text #14

Max Range: 4.1445. Min Range: -4.1445

Max Act: 2.0076. Min Act: -0.0000

Data Index: 1556630 (Python Code)

Max Activating Token Index: 748

Text #15

Max Range: 4.1445. Min Range: -4.1445

Max Act: 1.7867. Min Act: -0.0000

Data Index: 279217 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 4.1445. Min Range: -4.1445

Max Act: 1.8552. Min Act: -0.0000

Data Index: 1649593 (Python Code)

Max Activating Token Index: 980

Text #17

Max Range: 4.1445. Min Range: -4.1445

Max Act: 1.6529. Min Act: -0.0000

Data Index: 571449 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 4.1445. Min Range: -4.1445

Max Act: 1.7156. Min Act: -0.0000

Data Index: 1162794 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 4.1445. Min Range: -4.1445

Max Act: 1.4189. Min Act: -0.0000

Data Index: 198569 (C4 (Web Text))

Max Activating Token Index: 767