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

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

Neuron 4904 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: 0.3582. Min Range: -0.3582

Max Act: 0.3423. Min Act: -0.0000

Data Index: 1636605 (Python Code)

Max Activating Token Index: 318

Text #1

Max Range: 0.3582. Min Range: -0.3582

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1528447 (Python Code)

Max Activating Token Index: 496

Text #2

Max Range: 0.3582. Min Range: -0.3582

Max Act: 0.3582. Min Act: -0.0000

Data Index: 1229709 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 0.3582. Min Range: -0.3582

Max Act: 0.3343. Min Act: -0.0000

Data Index: 853389 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 0.3582. Min Range: -0.3582

Max Act: 0.3344. Min Act: -0.0000

Data Index: 419914 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 0.3582. Min Range: -0.3582

Max Act: 0.3380. Min Act: -0.0000

Data Index: 1558082 (Python Code)

Max Activating Token Index: 616

Text #6

Max Range: 0.3582. Min Range: -0.3582

Max Act: 0.3319. Min Act: -0.0000

Data Index: 358757 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.3582. Min Range: -0.3582

Max Act: 0.3128. Min Act: -0.0000

Data Index: 1518804 (Python Code)

Max Activating Token Index: 508

Text #8

Max Range: 0.3582. Min Range: -0.3582

Max Act: 0.3237. Min Act: -0.0000

Data Index: 1379803 (Python Code)

Max Activating Token Index: 274

Text #9

Max Range: 0.3582. Min Range: -0.3582

Max Act: 0.3403. Min Act: -0.0000

Data Index: 638240 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.3582. Min Range: -0.3582

Max Act: 0.3123. Min Act: -0.0000

Data Index: 818212 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.3582. Min Range: -0.3582

Max Act: 0.2987. Min Act: -0.0000

Data Index: 1170168 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 0.3582. Min Range: -0.3582

Max Act: 0.3104. Min Act: -0.0000

Data Index: 588470 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 0.3582. Min Range: -0.3582

Max Act: 0.2989. Min Act: -0.0000

Data Index: 1606428 (Python Code)

Max Activating Token Index: 326

Text #14

Max Range: 0.3582. Min Range: -0.3582

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1560124 (Python Code)

Max Activating Token Index: 53

Text #15

Max Range: 0.3582. Min Range: -0.3582

Max Act: 0.2999. Min Act: -0.0000

Data Index: 299378 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 0.3582. Min Range: -0.3582

Max Act: 0.3022. Min Act: -0.0000

Data Index: 42991 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.3582. Min Range: -0.3582

Max Act: 0.3102. Min Act: -0.0000

Data Index: 106493 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.3582. Min Range: -0.3582

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1547195 (Python Code)

Max Activating Token Index: 881

Text #19

Max Range: 0.3582. Min Range: -0.3582

Max Act: 0.2786. Min Act: -0.0000

Data Index: 1624988 (Python Code)

Max Activating Token Index: 510