Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5059 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5256. Min Range: -1.5256

Max Act: 1.2435. Min Act: -0.0001

Data Index: 197556 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 1.5256. Min Range: -1.5256

Max Act: 1.5256. Min Act: -0.0001

Data Index: 1100347 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 1.5256. Min Range: -1.5256

Max Act: 1.2250. Min Act: -0.0001

Data Index: 215017 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 1.5256. Min Range: -1.5256

Max Act: 1.2868. Min Act: -0.0001

Data Index: 503981 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 1.5256. Min Range: -1.5256

Max Act: 1.3457. Min Act: -0.0001

Data Index: 85998 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 1.5256. Min Range: -1.5256

Max Act: 1.2506. Min Act: -0.0001

Data Index: 690704 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 1.5256. Min Range: -1.5256

Max Act: 1.3665. Min Act: -0.0001

Data Index: 61324 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 1.5256. Min Range: -1.5256

Max Act: 1.2531. Min Act: -0.0001

Data Index: 1108377 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 1.5256. Min Range: -1.5256

Max Act: 1.4203. Min Act: -0.0001

Data Index: 1074732 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 1.5256. Min Range: -1.5256

Max Act: 1.2816. Min Act: -0.0001

Data Index: 1283110 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 1.5256. Min Range: -1.5256

Max Act: 1.2075. Min Act: -0.0001

Data Index: 788369 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 1.5256. Min Range: -1.5256

Max Act: 1.3172. Min Act: -0.0001

Data Index: 1085998 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 1.5256. Min Range: -1.5256

Max Act: 1.2442. Min Act: -0.0001

Data Index: 793537 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 1.5256. Min Range: -1.5256

Max Act: 1.2215. Min Act: -0.0001

Data Index: 650917 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 1.5256. Min Range: -1.5256

Max Act: 1.2362. Min Act: -0.0001

Data Index: 94168 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 1.5256. Min Range: -1.5256

Max Act: 1.2465. Min Act: -0.0001

Data Index: 725069 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 1.5256. Min Range: -1.5256

Max Act: 1.3302. Min Act: -0.0001

Data Index: 810475 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 1.5256. Min Range: -1.5256

Max Act: 1.3561. Min Act: -0.0001

Data Index: 52847 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 1.5256. Min Range: -1.5256

Max Act: 1.1020. Min Act: -0.0001

Data Index: 1242210 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 1.5256. Min Range: -1.5256

Max Act: 1.3375. Min Act: -0.0001

Data Index: 98084 (C4 (Web Text))

Max Activating Token Index: 69