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

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

Neuron 1422 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.4070. Min Act: -0.0001

Data Index: 1400045 (Python Code)

Max Activating Token Index: 863

Text #1

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3649. Min Act: -0.0001

Data Index: 1414866 (Python Code)

Max Activating Token Index: 958

Text #2

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3797. Min Act: -0.0001

Data Index: 1572750 (Python Code)

Max Activating Token Index: 429

Text #3

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3925. Min Act: -0.0001

Data Index: 1478820 (Python Code)

Max Activating Token Index: 22

Text #4

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3732. Min Act: -0.0001

Data Index: 1408440 (Python Code)

Max Activating Token Index: 840

Text #5

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3449. Min Act: -0.0001

Data Index: 1599978 (Python Code)

Max Activating Token Index: 220

Text #6

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3768. Min Act: -0.0001

Data Index: 1480974 (Python Code)

Max Activating Token Index: 251

Text #7

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3600. Min Act: -0.0001

Data Index: 1637287 (Python Code)

Max Activating Token Index: 546

Text #8

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3501. Min Act: -0.0001

Data Index: 1518231 (Python Code)

Max Activating Token Index: 125

Text #9

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3219. Min Act: -0.0001

Data Index: 1379763 (Python Code)

Max Activating Token Index: 1013

Text #10

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3438. Min Act: -0.0001

Data Index: 1640569 (Python Code)

Max Activating Token Index: 963

Text #11

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3628. Min Act: -0.0001

Data Index: 1541444 (Python Code)

Max Activating Token Index: 354

Text #12

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3609. Min Act: -0.0001

Data Index: 1441461 (Python Code)

Max Activating Token Index: 224

Text #13

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3408. Min Act: -0.0001

Data Index: 1491751 (Python Code)

Max Activating Token Index: 1005

Text #14

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3401. Min Act: -0.0001

Data Index: 1504240 (Python Code)

Max Activating Token Index: 996

Text #15

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3801. Min Act: -0.0001

Data Index: 1451848 (Python Code)

Max Activating Token Index: 906

Text #16

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3544. Min Act: -0.0001

Data Index: 1396326 (Python Code)

Max Activating Token Index: 1005

Text #17

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3289. Min Act: -0.0001

Data Index: 1577792 (Python Code)

Max Activating Token Index: 719

Text #18

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3460. Min Act: -0.0001

Data Index: 1640998 (Python Code)

Max Activating Token Index: 774

Text #19

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3131. Min Act: -0.0001

Data Index: 1450327 (Python Code)

Max Activating Token Index: 836