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

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

Neuron 3456 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1499. Min Range: -3.1499

Max Act: 3.1499. Min Act: -0.0000

Data Index: 520240 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 3.1499. Min Range: -3.1499

Max Act: 2.8942. Min Act: -0.0000

Data Index: 928876 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 3.1499. Min Range: -3.1499

Max Act: 2.8418. Min Act: -0.0000

Data Index: 1483417 (Python Code)

Max Activating Token Index: 845

Text #3

Max Range: 3.1499. Min Range: -3.1499

Max Act: 2.6137. Min Act: -0.0000

Data Index: 798877 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 3.1499. Min Range: -3.1499

Max Act: 2.6853. Min Act: -0.0000

Data Index: 1643134 (Python Code)

Max Activating Token Index: 542

Text #5

Max Range: 3.1499. Min Range: -3.1499

Max Act: 2.6932. Min Act: -0.0000

Data Index: 1332595 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 3.1499. Min Range: -3.1499

Max Act: 2.6734. Min Act: -0.0000

Data Index: 76545 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.1499. Min Range: -3.1499

Max Act: 2.5861. Min Act: -0.0000

Data Index: 115059 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 3.1499. Min Range: -3.1499

Max Act: 2.4318. Min Act: -0.0000

Data Index: 1549982 (Python Code)

Max Activating Token Index: 534

Text #9

Max Range: 3.1499. Min Range: -3.1499

Max Act: 2.6936. Min Act: -0.0000

Data Index: 982238 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 3.1499. Min Range: -3.1499

Max Act: 2.5647. Min Act: -0.0000

Data Index: 37364 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 3.1499. Min Range: -3.1499

Max Act: 2.6689. Min Act: -0.0000

Data Index: 1354770 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 3.1499. Min Range: -3.1499

Max Act: 2.5267. Min Act: -0.0000

Data Index: 1199795 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 3.1499. Min Range: -3.1499

Max Act: 2.5247. Min Act: -0.0000

Data Index: 1509940 (Python Code)

Max Activating Token Index: 623

Text #14

Max Range: 3.1499. Min Range: -3.1499

Max Act: 2.6053. Min Act: -0.0000

Data Index: 1564109 (Python Code)

Max Activating Token Index: 333

Text #15

Max Range: 3.1499. Min Range: -3.1499

Max Act: 2.4652. Min Act: -0.0000

Data Index: 1432172 (Python Code)

Max Activating Token Index: 394

Text #16

Max Range: 3.1499. Min Range: -3.1499

Max Act: 2.4630. Min Act: -0.0000

Data Index: 1205134 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 3.1499. Min Range: -3.1499

Max Act: 2.3221. Min Act: -0.0000

Data Index: 1481893 (Python Code)

Max Activating Token Index: 813

Text #18

Max Range: 3.1499. Min Range: -3.1499

Max Act: 2.2755. Min Act: -0.0000

Data Index: 1476170 (Python Code)

Max Activating Token Index: 247

Text #19

Max Range: 3.1499. Min Range: -3.1499

Max Act: 2.4014. Min Act: -0.0000

Data Index: 1394063 (Python Code)

Max Activating Token Index: 262