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

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

Neuron 4207 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3146. Min Range: -4.3146

Max Act: 4.3102. Min Act: -0.0000

Data Index: 1572488 (Python Code)

Max Activating Token Index: 703

Text #1

Max Range: 4.3146. Min Range: -4.3146

Max Act: 4.3146. Min Act: -0.0000

Data Index: 1509434 (Python Code)

Max Activating Token Index: 502

Text #2

Max Range: 4.3146. Min Range: -4.3146

Max Act: 4.0888. Min Act: -0.0000

Data Index: 1640362 (Python Code)

Max Activating Token Index: 172

Text #3

Max Range: 4.3146. Min Range: -4.3146

Max Act: 3.8012. Min Act: -0.0000

Data Index: 1413060 (Python Code)

Max Activating Token Index: 360

Text #4

Max Range: 4.3146. Min Range: -4.3146

Max Act: 3.6557. Min Act: -0.0000

Data Index: 1396364 (Python Code)

Max Activating Token Index: 182

Text #5

Max Range: 4.3146. Min Range: -4.3146

Max Act: 3.8045. Min Act: -0.0000

Data Index: 1256658 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 4.3146. Min Range: -4.3146

Max Act: 3.5877. Min Act: -0.0000

Data Index: 1399462 (Python Code)

Max Activating Token Index: 373

Text #7

Max Range: 4.3146. Min Range: -4.3146

Max Act: 3.5954. Min Act: -0.0000

Data Index: 1535484 (Python Code)

Max Activating Token Index: 326

Text #8

Max Range: 4.3146. Min Range: -4.3146

Max Act: 3.5727. Min Act: -0.0000

Data Index: 1622171 (Python Code)

Max Activating Token Index: 643

Text #9

Max Range: 4.3146. Min Range: -4.3146

Max Act: 3.5568. Min Act: -0.0000

Data Index: 1442770 (Python Code)

Max Activating Token Index: 871

Text #10

Max Range: 4.3146. Min Range: -4.3146

Max Act: 3.4027. Min Act: -0.0000

Data Index: 1401729 (Python Code)

Max Activating Token Index: 926

Text #11

Max Range: 4.3146. Min Range: -4.3146

Max Act: 3.3901. Min Act: -0.0000

Data Index: 1545028 (Python Code)

Max Activating Token Index: 490

Text #12

Max Range: 4.3146. Min Range: -4.3146

Max Act: 3.0614. Min Act: -0.0000

Data Index: 1589633 (Python Code)

Max Activating Token Index: 530

Text #13

Max Range: 4.3146. Min Range: -4.3146

Max Act: 3.3231. Min Act: -0.0000

Data Index: 1556367 (Python Code)

Max Activating Token Index: 871

Text #14

Max Range: 4.3146. Min Range: -4.3146

Max Act: 3.1373. Min Act: -0.0000

Data Index: 1456132 (Python Code)

Max Activating Token Index: 702

Text #15

Max Range: 4.3146. Min Range: -4.3146

Max Act: 3.0948. Min Act: -0.0000

Data Index: 1465417 (Python Code)

Max Activating Token Index: 194

Text #16

Max Range: 4.3146. Min Range: -4.3146

Max Act: 3.2669. Min Act: -0.0000

Data Index: 1378357 (Python Code)

Max Activating Token Index: 347

Text #17

Max Range: 4.3146. Min Range: -4.3146

Max Act: 2.9255. Min Act: -0.0000

Data Index: 437717 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 4.3146. Min Range: -4.3146

Max Act: 3.0483. Min Act: -0.0000

Data Index: 1368310 (Python Code)

Max Activating Token Index: 756

Text #19

Max Range: 4.3146. Min Range: -4.3146

Max Act: 3.0610. Min Act: -0.0000

Data Index: 1550843 (Python Code)

Max Activating Token Index: 181