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

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

Neuron 6131 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.8800. Min Act: -0.0001

Data Index: 254785 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.5116. Min Act: -0.0001

Data Index: 94274 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.4682. Min Act: -0.0001

Data Index: 830239 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.3933. Min Act: -0.0001

Data Index: 1562052 (Python Code)

Max Activating Token Index: 791

Text #4

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.3902. Min Act: -0.0001

Data Index: 81046 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.2524. Min Act: -0.0001

Data Index: 1503208 (Python Code)

Max Activating Token Index: 264

Text #6

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.3611. Min Act: -0.0001

Data Index: 1475133 (Python Code)

Max Activating Token Index: 739

Text #7

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.2816. Min Act: -0.0001

Data Index: 1320952 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.4327. Min Act: -0.0001

Data Index: 250380 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.3844. Min Act: -0.0001

Data Index: 906402 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.2559. Min Act: -0.0001

Data Index: 1497171 (Python Code)

Max Activating Token Index: 930

Text #11

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.2533. Min Act: -0.0001

Data Index: 338535 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.3342. Min Act: -0.0001

Data Index: 628652 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.2458. Min Act: -0.0001

Data Index: 911847 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.3272. Min Act: -0.0001

Data Index: 1604993 (Python Code)

Max Activating Token Index: 178

Text #15

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.2504. Min Act: -0.0001

Data Index: 1525281 (Python Code)

Max Activating Token Index: 225

Text #16

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.2687. Min Act: -0.0001

Data Index: 601883 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.1913. Min Act: -0.0001

Data Index: 1040049 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.1836. Min Act: -0.0001

Data Index: 258459 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 1.8800. Min Range: -1.8800

Max Act: 1.2269. Min Act: -0.0001

Data Index: 438306 (C4 (Web Text))

Max Activating Token Index: 794