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

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

Neuron 1031 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: 1.3457. Min Range: -1.3457

Max Act: 1.3457. Min Act: -0.0000

Data Index: 1177994 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 1.3457. Min Range: -1.3457

Max Act: 1.1890. Min Act: -0.0000

Data Index: 397312 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 1.3457. Min Range: -1.3457

Max Act: 1.1774. Min Act: -0.0001

Data Index: 988059 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 1.3457. Min Range: -1.3457

Max Act: 1.0890. Min Act: -0.0000

Data Index: 414850 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 1.3457. Min Range: -1.3457

Max Act: 1.1361. Min Act: -0.0001

Data Index: 7997 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 1.3457. Min Range: -1.3457

Max Act: 1.0915. Min Act: -0.0000

Data Index: 172994 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 1.3457. Min Range: -1.3457

Max Act: 1.0861. Min Act: -0.0001

Data Index: 1290309 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 1.3457. Min Range: -1.3457

Max Act: 1.0542. Min Act: -0.0000

Data Index: 732454 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 1.3457. Min Range: -1.3457

Max Act: 1.0032. Min Act: -0.0000

Data Index: 641501 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 1.3457. Min Range: -1.3457

Max Act: 0.9864. Min Act: -0.0000

Data Index: 1030378 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 1.3457. Min Range: -1.3457

Max Act: 1.0170. Min Act: -0.0000

Data Index: 250506 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 1.3457. Min Range: -1.3457

Max Act: 0.9232. Min Act: -0.0000

Data Index: 553078 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 1.3457. Min Range: -1.3457

Max Act: 1.0104. Min Act: -0.0000

Data Index: 304816 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 1.3457. Min Range: -1.3457

Max Act: 0.9814. Min Act: -0.0000

Data Index: 868931 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 1.3457. Min Range: -1.3457

Max Act: 0.9635. Min Act: -0.0001

Data Index: 1290481 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 1.3457. Min Range: -1.3457

Max Act: 0.9299. Min Act: -0.0000

Data Index: 567889 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 1.3457. Min Range: -1.3457

Max Act: 1.0128. Min Act: -0.0001

Data Index: 1084863 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 1.3457. Min Range: -1.3457

Max Act: 1.0121. Min Act: -0.0000

Data Index: 1222316 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 1.3457. Min Range: -1.3457

Max Act: 0.9237. Min Act: -0.0000

Data Index: 539503 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 1.3457. Min Range: -1.3457

Max Act: 0.9397. Min Act: -0.0000

Data Index: 580372 (C4 (Web Text))

Max Activating Token Index: 286