Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 480 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.5477. Min Act: 0.0000

Data Index: 1651967 (Python Code)

Max Activating Token Index: 942

Text #1

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4924. Min Act: -0.0000

Data Index: 1433461 (Python Code)

Max Activating Token Index: 815

Text #2

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4447. Min Act: 0.0000

Data Index: 76419 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4223. Min Act: -0.0000

Data Index: 764692 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4066. Min Act: -0.0000

Data Index: 855360 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3988. Min Act: -0.0000

Data Index: 709951 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3707. Min Act: -0.0000

Data Index: 1551344 (Python Code)

Max Activating Token Index: 534

Text #7

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4053. Min Act: 0.0000

Data Index: 1477695 (Python Code)

Max Activating Token Index: 986

Text #8

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3626. Min Act: -0.0000

Data Index: 1209597 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3831. Min Act: -0.0000

Data Index: 1378353 (Python Code)

Max Activating Token Index: 624

Text #10

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1348056 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3432. Min Act: -0.0000

Data Index: 1610728 (Python Code)

Max Activating Token Index: 405

Text #12

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3399. Min Act: -0.0000

Data Index: 340629 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3307. Min Act: -0.0000

Data Index: 81555 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3652. Min Act: -0.0000

Data Index: 872470 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3433. Min Act: 0.0000

Data Index: 928916 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3452. Min Act: -0.0000

Data Index: 146214 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3504. Min Act: 0.0001

Data Index: 949410 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3304. Min Act: 0.0000

Data Index: 133603 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3507. Min Act: -0.0000

Data Index: 887280 (C4 (Web Text))

Max Activating Token Index: 520