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

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

Neuron 921 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1128. Min Act: -0.0002

Data Index: 1447781 (Python Code)

Max Activating Token Index: 173

Text #1

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1138. Min Act: -0.0002

Data Index: 1420388 (Python Code)

Max Activating Token Index: 175

Text #2

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1119. Min Act: -0.0002

Data Index: 1536128 (Python Code)

Max Activating Token Index: 102

Text #3

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1078. Min Act: -0.0002

Data Index: 1422342 (Python Code)

Max Activating Token Index: 198

Text #4

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1074. Min Act: -0.0002

Data Index: 1572804 (Python Code)

Max Activating Token Index: 123

Text #5

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1041. Min Act: -0.0002

Data Index: 1435980 (Python Code)

Max Activating Token Index: 91

Text #6

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1029. Min Act: -0.0002

Data Index: 1556375 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1010. Min Act: -0.0002

Data Index: 1564875 (Python Code)

Max Activating Token Index: 409

Text #8

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1019. Min Act: -0.0002

Data Index: 1463106 (Python Code)

Max Activating Token Index: 609

Text #9

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1031. Min Act: -0.0002

Data Index: 1608140 (Python Code)

Max Activating Token Index: 729

Text #10

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1021. Min Act: -0.0002

Data Index: 1439643 (Python Code)

Max Activating Token Index: 47

Text #11

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0986. Min Act: -0.0002

Data Index: 1452508 (Python Code)

Max Activating Token Index: 591

Text #12

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0983. Min Act: -0.0002

Data Index: 1616951 (Python Code)

Max Activating Token Index: 201

Text #13

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0978. Min Act: -0.0002

Data Index: 1597886 (Python Code)

Max Activating Token Index: 61

Text #14

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0995. Min Act: -0.0002

Data Index: 1453821 (Python Code)

Max Activating Token Index: 470

Text #15

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0969. Min Act: -0.0002

Data Index: 1514423 (Python Code)

Max Activating Token Index: 492

Text #16

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1581565 (Python Code)

Max Activating Token Index: 609

Text #17

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0964. Min Act: -0.0002

Data Index: 1414684 (Python Code)

Max Activating Token Index: 475

Text #18

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0966. Min Act: -0.0002

Data Index: 1602584 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0952. Min Act: -0.0002

Data Index: 1545309 (Python Code)

Max Activating Token Index: 333