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

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

Neuron 3449 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0946. Min Range: -1.0946

Max Act: 1.0946. Min Act: -0.0001

Data Index: 1103646 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 1.0946. Min Range: -1.0946

Max Act: 1.0823. Min Act: -0.0001

Data Index: 1165893 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.9828. Min Act: -0.0000

Data Index: 77491 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 1.0946. Min Range: -1.0946

Max Act: 1.0070. Min Act: -0.0000

Data Index: 43000 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.9660. Min Act: -0.0000

Data Index: 702949 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.9800. Min Act: -0.0000

Data Index: 878428 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.9370. Min Act: -0.0001

Data Index: 20360 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.9819. Min Act: -0.0000

Data Index: 1058689 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.9344. Min Act: -0.0000

Data Index: 147323 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.8721. Min Act: -0.0000

Data Index: 813386 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 1.0946. Min Range: -1.0946

Max Act: 1.0170. Min Act: -0.0001

Data Index: 1332024 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.8510. Min Act: -0.0000

Data Index: 709120 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.8768. Min Act: -0.0000

Data Index: 246117 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.9431. Min Act: -0.0000

Data Index: 77226 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.8300. Min Act: -0.0000

Data Index: 1197591 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.8194. Min Act: -0.0001

Data Index: 481562 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.8831. Min Act: -0.0000

Data Index: 1052570 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.8627. Min Act: -0.0000

Data Index: 987116 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.8508. Min Act: -0.0000

Data Index: 442221 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.8249. Min Act: -0.0000

Data Index: 954944 (C4 (Web Text))

Max Activating Token Index: 4