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

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

Neuron 5775 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: 0.1104. Min Range: -0.1104

Max Act: 0.1104. Min Act: -0.0002

Data Index: 1383520 (Python Code)

Max Activating Token Index: 134

Text #1

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.1074. Min Act: -0.0002

Data Index: 199031 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.1021. Min Act: -0.0002

Data Index: 587146 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.1009. Min Act: -0.0002

Data Index: 269654 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0998. Min Act: -0.0002

Data Index: 273220 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0991. Min Act: -0.0002

Data Index: 1412144 (Python Code)

Max Activating Token Index: 428

Text #6

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0975. Min Act: -0.0002

Data Index: 1508392 (Python Code)

Max Activating Token Index: 536

Text #7

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0979. Min Act: -0.0002

Data Index: 1462044 (Python Code)

Max Activating Token Index: 176

Text #8

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0949. Min Act: -0.0002

Data Index: 898736 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0951. Min Act: -0.0002

Data Index: 724302 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0934. Min Act: -0.0002

Data Index: 629203 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0931. Min Act: -0.0002

Data Index: 1579811 (Python Code)

Max Activating Token Index: 250

Text #12

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0945. Min Act: -0.0002

Data Index: 1081628 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0918. Min Act: -0.0002

Data Index: 140751 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0901. Min Act: -0.0002

Data Index: 961096 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0906. Min Act: -0.0002

Data Index: 1426061 (Python Code)

Max Activating Token Index: 458

Text #16

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0921. Min Act: -0.0002

Data Index: 524915 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0913. Min Act: -0.0002

Data Index: 878638 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0921. Min Act: -0.0002

Data Index: 1523344 (Python Code)

Max Activating Token Index: 813

Text #19

Max Range: 0.1104. Min Range: -0.1104

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1431171 (Python Code)

Max Activating Token Index: 639