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

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

Neuron 442 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.9801. Min Act: -0.0000

Data Index: 669550 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.9531. Min Act: -0.0000

Data Index: 760911 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.7802. Min Act: -0.0000

Data Index: 1116428 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.8825. Min Act: -0.0000

Data Index: 156729 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.7163. Min Act: 0.0000

Data Index: 1593946 (Python Code)

Max Activating Token Index: 98

Text #5

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.6269. Min Act: -0.0000

Data Index: 1407695 (Python Code)

Max Activating Token Index: 167

Text #6

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.5737. Min Act: -0.0000

Data Index: 1437798 (Python Code)

Max Activating Token Index: 420

Text #7

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.5774. Min Act: -0.0000

Data Index: 1532480 (Python Code)

Max Activating Token Index: 240

Text #8

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1599281 (Python Code)

Max Activating Token Index: 264

Text #9

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.5419. Min Act: 0.0000

Data Index: 1383143 (Python Code)

Max Activating Token Index: 122

Text #10

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1363102 (Python Code)

Max Activating Token Index: 165

Text #11

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.5848. Min Act: 0.0000

Data Index: 1516581 (Python Code)

Max Activating Token Index: 350

Text #12

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.5150. Min Act: -0.0000

Data Index: 186187 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.5083. Min Act: -0.0000

Data Index: 1465156 (Python Code)

Max Activating Token Index: 263

Text #14

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.4842. Min Act: -0.0000

Data Index: 1533696 (Python Code)

Max Activating Token Index: 535

Text #15

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.4873. Min Act: -0.0000

Data Index: 1610064 (Python Code)

Max Activating Token Index: 116

Text #16

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.4878. Min Act: -0.0000

Data Index: 1391909 (Python Code)

Max Activating Token Index: 225

Text #17

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.4818. Min Act: -0.0000

Data Index: 1503029 (Python Code)

Max Activating Token Index: 227

Text #18

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1444946 (Python Code)

Max Activating Token Index: 374

Text #19

Max Range: 0.9801. Min Range: -0.9801

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1536955 (Python Code)

Max Activating Token Index: 63