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

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

Neuron 2081 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3891. Min Range: -2.3891

Max Act: 2.3891. Min Act: -0.0000

Data Index: 1106694 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 2.3891. Min Range: -2.3891

Max Act: 2.2878. Min Act: -0.0000

Data Index: 1080868 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 2.3891. Min Range: -2.3891

Max Act: 2.3464. Min Act: -0.0000

Data Index: 1521900 (Python Code)

Max Activating Token Index: 899

Text #3

Max Range: 2.3891. Min Range: -2.3891

Max Act: 2.0132. Min Act: -0.0000

Data Index: 1637561 (Python Code)

Max Activating Token Index: 237

Text #4

Max Range: 2.3891. Min Range: -2.3891

Max Act: 1.9115. Min Act: -0.0000

Data Index: 1274846 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 2.3891. Min Range: -2.3891

Max Act: 1.8953. Min Act: -0.0000

Data Index: 1604821 (Python Code)

Max Activating Token Index: 324

Text #6

Max Range: 2.3891. Min Range: -2.3891

Max Act: 1.9880. Min Act: -0.0000

Data Index: 1567883 (Python Code)

Max Activating Token Index: 253

Text #7

Max Range: 2.3891. Min Range: -2.3891

Max Act: 1.9010. Min Act: -0.0000

Data Index: 1467856 (Python Code)

Max Activating Token Index: 605

Text #8

Max Range: 2.3891. Min Range: -2.3891

Max Act: 1.8375. Min Act: -0.0000

Data Index: 1463612 (Python Code)

Max Activating Token Index: 111

Text #9

Max Range: 2.3891. Min Range: -2.3891

Max Act: 1.6955. Min Act: -0.0000

Data Index: 275546 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 2.3891. Min Range: -2.3891

Max Act: 1.6058. Min Act: -0.0000

Data Index: 1571670 (Python Code)

Max Activating Token Index: 35

Text #11

Max Range: 2.3891. Min Range: -2.3891

Max Act: 1.6821. Min Act: -0.0000

Data Index: 834541 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 2.3891. Min Range: -2.3891

Max Act: 1.6736. Min Act: -0.0000

Data Index: 970570 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 2.3891. Min Range: -2.3891

Max Act: 1.6451. Min Act: -0.0000

Data Index: 1626858 (Python Code)

Max Activating Token Index: 286

Text #14

Max Range: 2.3891. Min Range: -2.3891

Max Act: 1.7294. Min Act: -0.0000

Data Index: 1526812 (Python Code)

Max Activating Token Index: 808

Text #15

Max Range: 2.3891. Min Range: -2.3891

Max Act: 1.6207. Min Act: -0.0000

Data Index: 224620 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 2.3891. Min Range: -2.3891

Max Act: 1.6327. Min Act: -0.0000

Data Index: 1374241 (Python Code)

Max Activating Token Index: 101

Text #17

Max Range: 2.3891. Min Range: -2.3891

Max Act: 1.5260. Min Act: -0.0000

Data Index: 1126475 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 2.3891. Min Range: -2.3891

Max Act: 1.4503. Min Act: -0.0000

Data Index: 724501 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 2.3891. Min Range: -2.3891

Max Act: 1.4346. Min Act: -0.0000

Data Index: 1556199 (Python Code)

Max Activating Token Index: 910