Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3833 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.5840. Min Act: -0.0001

Data Index: 1505229 (Python Code)

Max Activating Token Index: 147

Text #1

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.4484. Min Act: -0.0001

Data Index: 1535005 (Python Code)

Max Activating Token Index: 980

Text #2

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.3168. Min Act: -0.0001

Data Index: 1569434 (Python Code)

Max Activating Token Index: 344

Text #3

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.2920. Min Act: -0.0001

Data Index: 1405805 (Python Code)

Max Activating Token Index: 671

Text #4

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.2814. Min Act: -0.0001

Data Index: 327553 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.2903. Min Act: -0.0001

Data Index: 469153 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.2800. Min Act: -0.0001

Data Index: 1465951 (Python Code)

Max Activating Token Index: 540

Text #7

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.2731. Min Act: -0.0001

Data Index: 1372921 (Python Code)

Max Activating Token Index: 402

Text #8

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.2587. Min Act: -0.0001

Data Index: 1379667 (Python Code)

Max Activating Token Index: 24

Text #9

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.2495. Min Act: -0.0001

Data Index: 1513217 (Python Code)

Max Activating Token Index: 646

Text #10

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.2453. Min Act: -0.0001

Data Index: 1537023 (Python Code)

Max Activating Token Index: 33

Text #11

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.2531. Min Act: -0.0001

Data Index: 1541204 (Python Code)

Max Activating Token Index: 36

Text #12

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.2438. Min Act: -0.0001

Data Index: 1619411 (Python Code)

Max Activating Token Index: 903

Text #13

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.2405. Min Act: -0.0001

Data Index: 1528534 (Python Code)

Max Activating Token Index: 669

Text #14

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.2549. Min Act: -0.0001

Data Index: 1552069 (Python Code)

Max Activating Token Index: 53

Text #15

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.2687. Min Act: -0.0001

Data Index: 1488795 (Python Code)

Max Activating Token Index: 648

Text #16

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.2603. Min Act: -0.0001

Data Index: 1533762 (Python Code)

Max Activating Token Index: 142

Text #17

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.2512. Min Act: -0.0001

Data Index: 902938 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.2387. Min Act: -0.0001

Data Index: 1517812 (Python Code)

Max Activating Token Index: 51

Text #19

Max Range: 0.5840. Min Range: -0.5840

Max Act: 0.2207. Min Act: -0.0001

Data Index: 1168346 (C4 (Web Text))

Max Activating Token Index: 347