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

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

Neuron 3181 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.4521. Min Act: -0.0000

Data Index: 805086 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3648. Min Act: -0.0000

Data Index: 1555149 (Python Code)

Max Activating Token Index: 257

Text #2

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3467. Min Act: -0.0000

Data Index: 1554014 (Python Code)

Max Activating Token Index: 655

Text #3

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3295. Min Act: -0.0000

Data Index: 1459872 (Python Code)

Max Activating Token Index: 542

Text #4

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3217. Min Act: -0.0000

Data Index: 1502138 (Python Code)

Max Activating Token Index: 813

Text #5

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.3044. Min Act: -0.0000

Data Index: 1198226 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.2910. Min Act: 0.0000

Data Index: 1081846 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1443810 (Python Code)

Max Activating Token Index: 50

Text #8

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.2795. Min Act: -0.0000

Data Index: 99186 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.2764. Min Act: -0.0000

Data Index: 1153609 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1545502 (Python Code)

Max Activating Token Index: 377

Text #11

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1621209 (Python Code)

Max Activating Token Index: 393

Text #12

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.2594. Min Act: -0.0000

Data Index: 112411 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.2547. Min Act: -0.0000

Data Index: 1566287 (Python Code)

Max Activating Token Index: 144

Text #14

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1643356 (Python Code)

Max Activating Token Index: 590

Text #15

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.2610. Min Act: 0.0000

Data Index: 798512 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.2486. Min Act: -0.0000

Data Index: 134208 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.2491. Min Act: -0.0000

Data Index: 156214 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.2776. Min Act: -0.0000

Data Index: 1548141 (Python Code)

Max Activating Token Index: 1014

Text #19

Max Range: 0.4521. Min Range: -0.4521

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1578727 (Python Code)

Max Activating Token Index: 835