Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1128 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.9963. Min Act: -0.0001

Data Index: 1488903 (Python Code)

Max Activating Token Index: 791

Text #1

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.8864. Min Act: -0.0001

Data Index: 1549786 (Python Code)

Max Activating Token Index: 880

Text #2

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.8260. Min Act: -0.0000

Data Index: 1557626 (Python Code)

Max Activating Token Index: 190

Text #3

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.8203. Min Act: -0.0001

Data Index: 1387779 (Python Code)

Max Activating Token Index: 840

Text #4

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.7168. Min Act: -0.0001

Data Index: 1508133 (Python Code)

Max Activating Token Index: 577

Text #5

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.7863. Min Act: -0.0001

Data Index: 1578166 (Python Code)

Max Activating Token Index: 736

Text #6

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.7814. Min Act: -0.0001

Data Index: 1486592 (Python Code)

Max Activating Token Index: 110

Text #7

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.7725. Min Act: -0.0001

Data Index: 1467539 (Python Code)

Max Activating Token Index: 355

Text #8

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.7697. Min Act: -0.0001

Data Index: 1510204 (Python Code)

Max Activating Token Index: 805

Text #9

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.7640. Min Act: -0.0001

Data Index: 1634096 (Python Code)

Max Activating Token Index: 498

Text #10

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.7799. Min Act: -0.0000

Data Index: 1424081 (Python Code)

Max Activating Token Index: 226

Text #11

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.7329. Min Act: -0.0001

Data Index: 1475555 (Python Code)

Max Activating Token Index: 554

Text #12

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.7303. Min Act: -0.0001

Data Index: 1368309 (Python Code)

Max Activating Token Index: 933

Text #13

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.7417. Min Act: -0.0001

Data Index: 1519671 (Python Code)

Max Activating Token Index: 382

Text #14

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.7091. Min Act: -0.0001

Data Index: 1540950 (Python Code)

Max Activating Token Index: 878

Text #15

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.7459. Min Act: -0.0001

Data Index: 1611909 (Python Code)

Max Activating Token Index: 896

Text #16

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.7517. Min Act: -0.0001

Data Index: 1625993 (Python Code)

Max Activating Token Index: 234

Text #17

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.7489. Min Act: -0.0001

Data Index: 1434615 (Python Code)

Max Activating Token Index: 310

Text #18

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.7433. Min Act: -0.0001

Data Index: 1509049 (Python Code)

Max Activating Token Index: 155

Text #19

Max Range: 0.9963. Min Range: -0.9963

Max Act: 0.7389. Min Act: -0.0001

Data Index: 1424561 (Python Code)

Max Activating Token Index: 895