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

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

Neuron 2816 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7525. Min Range: -2.7525

Max Act: 2.7525. Min Act: -0.0000

Data Index: 1314603 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 2.7525. Min Range: -2.7525

Max Act: 2.5328. Min Act: -0.0000

Data Index: 1368274 (Python Code)

Max Activating Token Index: 166

Text #2

Max Range: 2.7525. Min Range: -2.7525

Max Act: 2.3973. Min Act: -0.0000

Data Index: 1575271 (Python Code)

Max Activating Token Index: 790

Text #3

Max Range: 2.7525. Min Range: -2.7525

Max Act: 2.3109. Min Act: -0.0000

Data Index: 219908 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 2.7525. Min Range: -2.7525

Max Act: 2.5787. Min Act: -0.0000

Data Index: 1032828 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 2.7525. Min Range: -2.7525

Max Act: 2.4192. Min Act: -0.0000

Data Index: 1433580 (Python Code)

Max Activating Token Index: 439

Text #6

Max Range: 2.7525. Min Range: -2.7525

Max Act: 2.3854. Min Act: -0.0000

Data Index: 1482631 (Python Code)

Max Activating Token Index: 827

Text #7

Max Range: 2.7525. Min Range: -2.7525

Max Act: 2.4664. Min Act: -0.0000

Data Index: 856733 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 2.7525. Min Range: -2.7525

Max Act: 2.4311. Min Act: -0.0000

Data Index: 1394521 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 2.7525. Min Range: -2.7525

Max Act: 2.4311. Min Act: -0.0000

Data Index: 1620478 (Python Code)

Max Activating Token Index: 9

Text #10

Max Range: 2.7525. Min Range: -2.7525

Max Act: 2.4040. Min Act: -0.0000

Data Index: 1408482 (Python Code)

Max Activating Token Index: 565

Text #11

Max Range: 2.7525. Min Range: -2.7525

Max Act: 2.3879. Min Act: -0.0000

Data Index: 708728 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 2.7525. Min Range: -2.7525

Max Act: 2.3828. Min Act: -0.0000

Data Index: 1635670 (Python Code)

Max Activating Token Index: 988

Text #13

Max Range: 2.7525. Min Range: -2.7525

Max Act: 2.3203. Min Act: -0.0000

Data Index: 1594811 (Python Code)

Max Activating Token Index: 74

Text #14

Max Range: 2.7525. Min Range: -2.7525

Max Act: 2.2966. Min Act: -0.0000

Data Index: 1430538 (Python Code)

Max Activating Token Index: 5

Text #15

Max Range: 2.7525. Min Range: -2.7525

Max Act: 2.2947. Min Act: -0.0000

Data Index: 1396203 (Python Code)

Max Activating Token Index: 334

Text #16

Max Range: 2.7525. Min Range: -2.7525

Max Act: 2.0310. Min Act: -0.0000

Data Index: 1457688 (Python Code)

Max Activating Token Index: 372

Text #17

Max Range: 2.7525. Min Range: -2.7525

Max Act: 2.3303. Min Act: -0.0000

Data Index: 1054926 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 2.7525. Min Range: -2.7525

Max Act: 2.1780. Min Act: -0.0000

Data Index: 817635 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 2.7525. Min Range: -2.7525

Max Act: 1.9707. Min Act: -0.0000

Data Index: 261435 (C4 (Web Text))

Max Activating Token Index: 893