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

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

Neuron 1536 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.3880. Min Act: -0.0000

Data Index: 401915 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.2296. Min Act: -0.0000

Data Index: 936334 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.0865. Min Act: -0.0001

Data Index: 430361 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.0697. Min Act: -0.0000

Data Index: 285009 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.0671. Min Act: -0.0000

Data Index: 777971 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.0638. Min Act: -0.0000

Data Index: 677604 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.0598. Min Act: -0.0000

Data Index: 636967 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.0632. Min Act: -0.0000

Data Index: 449467 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.1076. Min Act: -0.0001

Data Index: 988857 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.0577. Min Act: -0.0000

Data Index: 771805 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.0553. Min Act: -0.0000

Data Index: 667479 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.0559. Min Act: -0.0001

Data Index: 1407549 (Python Code)

Max Activating Token Index: 190

Text #12

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.0477. Min Act: -0.0000

Data Index: 1206464 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.0514. Min Act: -0.0000

Data Index: 579614 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.0496. Min Act: -0.0000

Data Index: 12105 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.0507. Min Act: -0.0000

Data Index: 238583 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.0469. Min Act: -0.0000

Data Index: 1266522 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.0519. Min Act: -0.0000

Data Index: 398110 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.0521. Min Act: -0.0000

Data Index: 261661 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.3880. Min Range: -0.3880

Max Act: 0.0512. Min Act: -0.0000

Data Index: 944427 (C4 (Web Text))

Max Activating Token Index: 612