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

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

Neuron 3960 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7434. Min Range: -2.7434

Max Act: 2.7434. Min Act: -0.0000

Data Index: 810215 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 2.7434. Min Range: -2.7434

Max Act: 2.4439. Min Act: -0.0000

Data Index: 384493 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 2.7434. Min Range: -2.7434

Max Act: 2.1520. Min Act: -0.0000

Data Index: 518807 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 2.7434. Min Range: -2.7434

Max Act: 2.5004. Min Act: -0.0000

Data Index: 1265940 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 2.7434. Min Range: -2.7434

Max Act: 2.2517. Min Act: -0.0000

Data Index: 1120311 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 2.7434. Min Range: -2.7434

Max Act: 2.3250. Min Act: -0.0000

Data Index: 856522 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 2.7434. Min Range: -2.7434

Max Act: 2.4250. Min Act: -0.0000

Data Index: 1224108 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 2.7434. Min Range: -2.7434

Max Act: 2.1663. Min Act: -0.0000

Data Index: 1213530 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 2.7434. Min Range: -2.7434

Max Act: 2.4020. Min Act: -0.0000

Data Index: 289831 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 2.7434. Min Range: -2.7434

Max Act: 2.1593. Min Act: -0.0000

Data Index: 970071 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 2.7434. Min Range: -2.7434

Max Act: 2.3411. Min Act: -0.0000

Data Index: 199494 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 2.7434. Min Range: -2.7434

Max Act: 2.3381. Min Act: -0.0000

Data Index: 612904 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 2.7434. Min Range: -2.7434

Max Act: 2.1049. Min Act: -0.0000

Data Index: 1253420 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 2.7434. Min Range: -2.7434

Max Act: 2.0805. Min Act: -0.0000

Data Index: 353495 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 2.7434. Min Range: -2.7434

Max Act: 2.2711. Min Act: -0.0000

Data Index: 1040419 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 2.7434. Min Range: -2.7434

Max Act: 2.1623. Min Act: -0.0000

Data Index: 756338 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 2.7434. Min Range: -2.7434

Max Act: 2.2721. Min Act: -0.0000

Data Index: 918610 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 2.7434. Min Range: -2.7434

Max Act: 2.2610. Min Act: -0.0000

Data Index: 1138606 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 2.7434. Min Range: -2.7434

Max Act: 2.1318. Min Act: -0.0000

Data Index: 902161 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 2.7434. Min Range: -2.7434

Max Act: 2.2375. Min Act: -0.0000

Data Index: 235375 (C4 (Web Text))

Max Activating Token Index: 89