Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 298 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3803. Min Range: -0.3803

Max Act: 0.3427. Min Act: -0.0001

Data Index: 1076635 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 0.3803. Min Range: -0.3803

Max Act: 0.3771. Min Act: -0.0001

Data Index: 820242 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 0.3803. Min Range: -0.3803

Max Act: 0.3720. Min Act: -0.0001

Data Index: 531837 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.3803. Min Range: -0.3803

Max Act: 0.3559. Min Act: -0.0001

Data Index: 3592 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 0.3803. Min Range: -0.3803

Max Act: 0.3803. Min Act: -0.0001

Data Index: 196149 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.3803. Min Range: -0.3803

Max Act: 0.3696. Min Act: -0.0000

Data Index: 973418 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.3803. Min Range: -0.3803

Max Act: 0.3662. Min Act: -0.0001

Data Index: 1498695 (Python Code)

Max Activating Token Index: 343

Text #7

Max Range: 0.3803. Min Range: -0.3803

Max Act: 0.3472. Min Act: -0.0001

Data Index: 1338094 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.3803. Min Range: -0.3803

Max Act: 0.3638. Min Act: -0.0001

Data Index: 552005 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 0.3803. Min Range: -0.3803

Max Act: 0.3493. Min Act: -0.0001

Data Index: 1420316 (Python Code)

Max Activating Token Index: 447

Text #10

Max Range: 0.3803. Min Range: -0.3803

Max Act: 0.3496. Min Act: -0.0001

Data Index: 341455 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 0.3803. Min Range: -0.3803

Max Act: 0.3385. Min Act: -0.0001

Data Index: 597900 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 0.3803. Min Range: -0.3803

Max Act: 0.3493. Min Act: -0.0001

Data Index: 1291918 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.3803. Min Range: -0.3803

Max Act: 0.3231. Min Act: -0.0001

Data Index: 164336 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 0.3803. Min Range: -0.3803

Max Act: 0.3430. Min Act: -0.0001

Data Index: 794590 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.3803. Min Range: -0.3803

Max Act: 0.3422. Min Act: -0.0000

Data Index: 467055 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.3803. Min Range: -0.3803

Max Act: 0.3533. Min Act: -0.0001

Data Index: 1595002 (Python Code)

Max Activating Token Index: 815

Text #17

Max Range: 0.3803. Min Range: -0.3803

Max Act: 0.3358. Min Act: -0.0001

Data Index: 941217 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.3803. Min Range: -0.3803

Max Act: 0.3134. Min Act: -0.0001

Data Index: 421744 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.3803. Min Range: -0.3803

Max Act: 0.3475. Min Act: -0.0000

Data Index: 315868 (C4 (Web Text))

Max Activating Token Index: 483