Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3803 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0995. Min Act: -0.0001

Data Index: 350935 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0948. Min Act: -0.0001

Data Index: 1099866 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1141652 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0831. Min Act: -0.0001

Data Index: 1289264 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0778. Min Act: -0.0001

Data Index: 103729 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0770. Min Act: -0.0001

Data Index: 391456 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0755. Min Act: -0.0001

Data Index: 578406 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0774. Min Act: -0.0001

Data Index: 598729 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0741. Min Act: -0.0001

Data Index: 583526 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1323126 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0758. Min Act: -0.0001

Data Index: 491843 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0701. Min Act: -0.0001

Data Index: 614257 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0727. Min Act: -0.0001

Data Index: 535525 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0677. Min Act: -0.0001

Data Index: 1655 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0751. Min Act: -0.0001

Data Index: 675814 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0712. Min Act: -0.0001

Data Index: 148064 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0738. Min Act: -0.0001

Data Index: 423429 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0636. Min Act: -0.0001

Data Index: 935244 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0682. Min Act: -0.0001

Data Index: 1050037 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0708. Min Act: -0.0001

Data Index: 399401 (C4 (Web Text))

Max Activating Token Index: 973