Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2027 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0507. Min Act: -0.0003

Data Index: 1090983 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1010452 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0474. Min Act: -0.0003

Data Index: 478850 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0473. Min Act: -0.0002

Data Index: 870477 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0451. Min Act: -0.0003

Data Index: 950063 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0448. Min Act: -0.0003

Data Index: 296581 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0436. Min Act: -0.0003

Data Index: 622752 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0439. Min Act: -0.0003

Data Index: 618246 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0434. Min Act: -0.0003

Data Index: 467770 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1299764 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0444. Min Act: -0.0003

Data Index: 1285564 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1214597 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0440. Min Act: -0.0003

Data Index: 624707 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1274328 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0431. Min Act: -0.0003

Data Index: 866882 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0421. Min Act: -0.0004

Data Index: 1007512 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0424. Min Act: -0.0002

Data Index: 425599 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1230723 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0414. Min Act: -0.0003

Data Index: 583048 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0428. Min Act: -0.0003

Data Index: 560342 (C4 (Web Text))

Max Activating Token Index: 1017