Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2039 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0574. Min Act: -0.0005

Data Index: 774497 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0522. Min Act: -0.0005

Data Index: 753262 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0492. Min Act: -0.0005

Data Index: 114536 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0475. Min Act: -0.0005

Data Index: 814533 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0445. Min Act: -0.0005

Data Index: 1354804 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0460. Min Act: -0.0005

Data Index: 841558 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0455. Min Act: -0.0005

Data Index: 1007029 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0444. Min Act: -0.0005

Data Index: 654414 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0450. Min Act: -0.0005

Data Index: 818008 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0448. Min Act: -0.0005

Data Index: 892707 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0477. Min Act: -0.0005

Data Index: 1305019 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0442. Min Act: -0.0005

Data Index: 886387 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0450. Min Act: -0.0005

Data Index: 1475068 (Python Code)

Max Activating Token Index: 374

Text #13

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0441. Min Act: -0.0005

Data Index: 844309 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0456. Min Act: -0.0005

Data Index: 1012658 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0464. Min Act: -0.0005

Data Index: 218721 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0436. Min Act: -0.0005

Data Index: 1364936 (Python Code)

Max Activating Token Index: 855

Text #17

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0436. Min Act: -0.0005

Data Index: 929430 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0438. Min Act: -0.0005

Data Index: 655807 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0442. Min Act: -0.0005

Data Index: 91209 (C4 (Web Text))

Max Activating Token Index: 36