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

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

Neuron 2775 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: 0.3579. Min Range: -0.3579

Max Act: 0.3579. Min Act: -0.0000

Data Index: 65024 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 0.3579. Min Range: -0.3579

Max Act: 0.3316. Min Act: -0.0000

Data Index: 145491 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 0.3579. Min Range: -0.3579

Max Act: 0.3141. Min Act: -0.0000

Data Index: 527318 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.3579. Min Range: -0.3579

Max Act: 0.3016. Min Act: -0.0000

Data Index: 926406 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.3579. Min Range: -0.3579

Max Act: 0.3037. Min Act: -0.0000

Data Index: 255297 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 0.3579. Min Range: -0.3579

Max Act: 0.3075. Min Act: -0.0000

Data Index: 142141 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 0.3579. Min Range: -0.3579

Max Act: 0.2940. Min Act: -0.0000

Data Index: 667044 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.3579. Min Range: -0.3579

Max Act: 0.2863. Min Act: -0.0000

Data Index: 934352 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.3579. Min Range: -0.3579

Max Act: 0.2605. Min Act: -0.0000

Data Index: 630818 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.3579. Min Range: -0.3579

Max Act: 0.2592. Min Act: -0.0000

Data Index: 657186 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.3579. Min Range: -0.3579

Max Act: 0.2596. Min Act: -0.0000

Data Index: 921181 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.3579. Min Range: -0.3579

Max Act: 0.2681. Min Act: -0.0000

Data Index: 824777 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.3579. Min Range: -0.3579

Max Act: 0.2582. Min Act: -0.0000

Data Index: 955910 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.3579. Min Range: -0.3579

Max Act: 0.2475. Min Act: -0.0000

Data Index: 1641 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.3579. Min Range: -0.3579

Max Act: 0.2463. Min Act: -0.0000

Data Index: 452498 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.3579. Min Range: -0.3579

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1160649 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.3579. Min Range: -0.3579

Max Act: 0.2480. Min Act: -0.0000

Data Index: 1130311 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 0.3579. Min Range: -0.3579

Max Act: 0.2467. Min Act: -0.0000

Data Index: 1237258 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.3579. Min Range: -0.3579

Max Act: 0.2317. Min Act: -0.0000

Data Index: 1324310 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.3579. Min Range: -0.3579

Max Act: 0.2413. Min Act: -0.0000

Data Index: 53893 (C4 (Web Text))

Max Activating Token Index: 660