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

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

Neuron 2885 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8434. Min Range: -2.8434

Max Act: 2.8434. Min Act: -0.0000

Data Index: 793133 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 2.8434. Min Range: -2.8434

Max Act: 2.3408. Min Act: -0.0000

Data Index: 368661 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 2.8434. Min Range: -2.8434

Max Act: 2.5680. Min Act: -0.0000

Data Index: 810786 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 2.8434. Min Range: -2.8434

Max Act: 2.5481. Min Act: -0.0000

Data Index: 602278 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 2.8434. Min Range: -2.8434

Max Act: 2.2588. Min Act: -0.0000

Data Index: 1140359 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 2.8434. Min Range: -2.8434

Max Act: 2.3400. Min Act: -0.0000

Data Index: 1250566 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 2.8434. Min Range: -2.8434

Max Act: 2.3894. Min Act: -0.0000

Data Index: 259606 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 2.8434. Min Range: -2.8434

Max Act: 2.3639. Min Act: -0.0000

Data Index: 929549 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 2.8434. Min Range: -2.8434

Max Act: 2.2536. Min Act: -0.0000

Data Index: 868012 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 2.8434. Min Range: -2.8434

Max Act: 2.3567. Min Act: -0.0000

Data Index: 724853 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 2.8434. Min Range: -2.8434

Max Act: 2.3449. Min Act: -0.0000

Data Index: 294977 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 2.8434. Min Range: -2.8434

Max Act: 2.4514. Min Act: -0.0000

Data Index: 1205987 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 2.8434. Min Range: -2.8434

Max Act: 2.2943. Min Act: -0.0000

Data Index: 453223 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 2.8434. Min Range: -2.8434

Max Act: 2.1701. Min Act: -0.0000

Data Index: 12981 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 2.8434. Min Range: -2.8434

Max Act: 2.2550. Min Act: -0.0000

Data Index: 127992 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 2.8434. Min Range: -2.8434

Max Act: 2.2545. Min Act: -0.0000

Data Index: 596848 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 2.8434. Min Range: -2.8434

Max Act: 2.2611. Min Act: -0.0000

Data Index: 1286904 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 2.8434. Min Range: -2.8434

Max Act: 2.2243. Min Act: -0.0000

Data Index: 814856 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 2.8434. Min Range: -2.8434

Max Act: 2.1273. Min Act: -0.0000

Data Index: 1109948 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 2.8434. Min Range: -2.8434

Max Act: 2.1959. Min Act: -0.0000

Data Index: 433658 (C4 (Web Text))

Max Activating Token Index: 532