Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 851 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1054. Min Range: -1.1054

Max Act: 1.1054. Min Act: -0.0001

Data Index: 640123 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 1.1054. Min Range: -1.1054

Max Act: 1.0487. Min Act: -0.0001

Data Index: 854651 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.9634. Min Act: -0.0001

Data Index: 1447935 (Python Code)

Max Activating Token Index: 486

Text #3

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.9978. Min Act: -0.0001

Data Index: 125182 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.9031. Min Act: -0.0001

Data Index: 1501653 (Python Code)

Max Activating Token Index: 579

Text #5

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.8986. Min Act: -0.0001

Data Index: 1615849 (Python Code)

Max Activating Token Index: 804

Text #6

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.8518. Min Act: -0.0001

Data Index: 1087262 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.9020. Min Act: -0.0001

Data Index: 1642019 (Python Code)

Max Activating Token Index: 599

Text #8

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.8612. Min Act: -0.0001

Data Index: 1200588 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.8452. Min Act: -0.0001

Data Index: 1459128 (Python Code)

Max Activating Token Index: 171

Text #10

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.8707. Min Act: -0.0001

Data Index: 680957 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.9278. Min Act: -0.0001

Data Index: 663909 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.8724. Min Act: -0.0001

Data Index: 1285069 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.9672. Min Act: -0.0001

Data Index: 1534399 (Python Code)

Max Activating Token Index: 724

Text #14

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.8653. Min Act: -0.0001

Data Index: 1435153 (Python Code)

Max Activating Token Index: 1004

Text #15

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.8596. Min Act: -0.0001

Data Index: 1511204 (Python Code)

Max Activating Token Index: 449

Text #16

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.8522. Min Act: -0.0001

Data Index: 1482932 (Python Code)

Max Activating Token Index: 271

Text #17

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.8520. Min Act: -0.0001

Data Index: 1526652 (Python Code)

Max Activating Token Index: 16

Text #18

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.8496. Min Act: -0.0001

Data Index: 1417708 (Python Code)

Max Activating Token Index: 705

Text #19

Max Range: 1.1054. Min Range: -1.1054

Max Act: 0.8148. Min Act: -0.0001

Data Index: 1066037 (C4 (Web Text))

Max Activating Token Index: 96