Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3788 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3878. Min Act: -0.0000

Data Index: 655968 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.4036. Min Act: -0.0000

Data Index: 785311 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1204175 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3663. Min Act: -0.0000

Data Index: 839861 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3522. Min Act: -0.0000

Data Index: 1351491 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3345. Min Act: -0.0000

Data Index: 508267 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3694. Min Act: -0.0000

Data Index: 1535684 (Python Code)

Max Activating Token Index: 791

Text #7

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1036189 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3774. Min Act: -0.0000

Data Index: 1286053 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3445. Min Act: -0.0000

Data Index: 790515 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3499. Min Act: -0.0000

Data Index: 434906 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3364. Min Act: -0.0000

Data Index: 609862 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3460. Min Act: -0.0000

Data Index: 1074270 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3357. Min Act: -0.0000

Data Index: 397738 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3321. Min Act: -0.0000

Data Index: 84548 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1324440 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3248. Min Act: -0.0000

Data Index: 735497 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3252. Min Act: -0.0000

Data Index: 456449 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3094. Min Act: -0.0000

Data Index: 847449 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.2962. Min Act: -0.0000

Data Index: 1257999 (C4 (Web Text))

Max Activating Token Index: 790