Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4073 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.9362. Min Act: -0.0000

Data Index: 869485 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.7322. Min Act: -0.0000

Data Index: 510955 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.7384. Min Act: -0.0000

Data Index: 502919 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.5856. Min Act: -0.0000

Data Index: 821339 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.5751. Min Act: -0.0000

Data Index: 309281 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.6805. Min Act: -0.0000

Data Index: 915716 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.5381. Min Act: -0.0000

Data Index: 297339 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.5621. Min Act: -0.0000

Data Index: 19383 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.5374. Min Act: -0.0000

Data Index: 1120087 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.4807. Min Act: -0.0000

Data Index: 822676 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.3228. Min Act: -0.0000

Data Index: 428116 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.4411. Min Act: -0.0000

Data Index: 1259592 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.5401. Min Act: -0.0001

Data Index: 640863 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.3608. Min Act: -0.0000

Data Index: 675534 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.3303. Min Act: -0.0000

Data Index: 708096 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.4359. Min Act: -0.0000

Data Index: 600432 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.0732. Min Act: -0.0000

Data Index: 620442 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.2990. Min Act: -0.0000

Data Index: 525794 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.1686. Min Act: -0.0000

Data Index: 126332 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 2.9362. Min Range: -2.9362

Max Act: 2.2778. Min Act: -0.0000

Data Index: 281072 (C4 (Web Text))

Max Activating Token Index: 738