Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 102 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1454211 (Python Code)

Max Activating Token Index: 105

Text #1

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0523. Min Act: -0.0003

Data Index: 1568962 (Python Code)

Max Activating Token Index: 498

Text #2

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0505. Min Act: -0.0003

Data Index: 582306 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0528. Min Act: -0.0002

Data Index: 19249 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0506. Min Act: -0.0003

Data Index: 1653933 (Python Code)

Max Activating Token Index: 141

Text #5

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0439. Min Act: -0.0003

Data Index: 1413527 (Python Code)

Max Activating Token Index: 936

Text #6

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0468. Min Act: -0.0003

Data Index: 1536855 (Python Code)

Max Activating Token Index: 199

Text #7

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1648570 (Python Code)

Max Activating Token Index: 330

Text #8

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0470. Min Act: -0.0003

Data Index: 1576163 (Python Code)

Max Activating Token Index: 802

Text #9

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0472. Min Act: -0.0003

Data Index: 1458474 (Python Code)

Max Activating Token Index: 82

Text #10

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1541004 (Python Code)

Max Activating Token Index: 580

Text #11

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0495. Min Act: -0.0003

Data Index: 1123559 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0480. Min Act: -0.0003

Data Index: 160392 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1563283 (Python Code)

Max Activating Token Index: 444

Text #14

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0473. Min Act: -0.0003

Data Index: 1550753 (Python Code)

Max Activating Token Index: 382

Text #15

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1361916 (Python Code)

Max Activating Token Index: 759

Text #16

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0472. Min Act: -0.0003

Data Index: 346229 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0452. Min Act: -0.0003

Data Index: 427605 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1615301 (Python Code)

Max Activating Token Index: 464

Text #19

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0457. Min Act: -0.0003

Data Index: 1563097 (Python Code)

Max Activating Token Index: 126