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

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

Neuron 1587 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: 0.0838. Min Range: -0.0838

Max Act: 0.0838. Min Act: -0.0002

Data Index: 1038230 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0546. Min Act: -0.0002

Data Index: 904866 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0545. Min Act: -0.0002

Data Index: 926285 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0542. Min Act: -0.0002

Data Index: 1141287 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0556. Min Act: -0.0002

Data Index: 88749 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1152036 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0523. Min Act: -0.0002

Data Index: 169989 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0480. Min Act: -0.0002

Data Index: 55007 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1280578 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1321388 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0465. Min Act: -0.0002

Data Index: 445398 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1213437 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1202023 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1147281 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1248347 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0463. Min Act: -0.0002

Data Index: 897487 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0479. Min Act: -0.0002

Data Index: 367720 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1278176 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1050434 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0455. Min Act: -0.0002

Data Index: 329399 (C4 (Web Text))

Max Activating Token Index: 703