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

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

Neuron 121 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0631. Min Act: -0.0002

Data Index: 941707 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0607. Min Act: -0.0002

Data Index: 687387 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0555. Min Act: -0.0002

Data Index: 834028 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0584. Min Act: -0.0002

Data Index: 381007 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1177640 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0508. Min Act: -0.0002

Data Index: 1588408 (Python Code)

Max Activating Token Index: 439

Text #6

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0504. Min Act: -0.0002

Data Index: 1325259 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0500. Min Act: -0.0002

Data Index: 685295 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0501. Min Act: -0.0002

Data Index: 32947 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1320800 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1277075 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0469. Min Act: -0.0002

Data Index: 375302 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0491. Min Act: -0.0002

Data Index: 1158330 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0460. Min Act: -0.0002

Data Index: 30365 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1285182 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0455. Min Act: -0.0002

Data Index: 721957 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1644170 (Python Code)

Max Activating Token Index: 139

Text #17

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0448. Min Act: -0.0002

Data Index: 84247 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0455. Min Act: -0.0002

Data Index: 238802 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0462. Min Act: -0.0002

Data Index: 518513 (C4 (Web Text))

Max Activating Token Index: 804