Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 549 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0538. Min Act: -0.0002

Data Index: 598169 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0545. Min Act: -0.0002

Data Index: 970998 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1343671 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1284960 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0514. Min Act: -0.0001

Data Index: 114099 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0514. Min Act: -0.0001

Data Index: 311969 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0514. Min Act: -0.0001

Data Index: 1179455 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0515. Min Act: -0.0001

Data Index: 724559 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1136463 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1233953 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0497. Min Act: -0.0001

Data Index: 583987 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0492. Min Act: -0.0002

Data Index: 746433 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0491. Min Act: -0.0002

Data Index: 931635 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0474. Min Act: -0.0001

Data Index: 694184 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0477. Min Act: -0.0002

Data Index: 280827 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0473. Min Act: -0.0001

Data Index: 132192 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0473. Min Act: -0.0002

Data Index: 874421 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0466. Min Act: -0.0002

Data Index: 89797 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0473. Min Act: -0.0002

Data Index: 405526 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0463. Min Act: -0.0001

Data Index: 127531 (C4 (Web Text))

Max Activating Token Index: 145