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

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

Neuron 5193 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: 4.5842. Min Range: -4.5842

Max Act: 4.5842. Min Act: -0.0000

Data Index: 1563069 (Python Code)

Max Activating Token Index: 770

Text #1

Max Range: 4.5842. Min Range: -4.5842

Max Act: 3.4132. Min Act: -0.0000

Data Index: 1531928 (Python Code)

Max Activating Token Index: 110

Text #2

Max Range: 4.5842. Min Range: -4.5842

Max Act: 3.2304. Min Act: -0.0000

Data Index: 1380932 (Python Code)

Max Activating Token Index: 396

Text #3

Max Range: 4.5842. Min Range: -4.5842

Max Act: 3.2915. Min Act: -0.0000

Data Index: 1579602 (Python Code)

Max Activating Token Index: 703

Text #4

Max Range: 4.5842. Min Range: -4.5842

Max Act: 2.9828. Min Act: -0.0000

Data Index: 1400109 (Python Code)

Max Activating Token Index: 947

Text #5

Max Range: 4.5842. Min Range: -4.5842

Max Act: 2.9686. Min Act: -0.0000

Data Index: 1565288 (Python Code)

Max Activating Token Index: 508

Text #6

Max Range: 4.5842. Min Range: -4.5842

Max Act: 3.0572. Min Act: -0.0000

Data Index: 1561186 (Python Code)

Max Activating Token Index: 498

Text #7

Max Range: 4.5842. Min Range: -4.5842

Max Act: 2.7543. Min Act: -0.0000

Data Index: 1564549 (Python Code)

Max Activating Token Index: 576

Text #8

Max Range: 4.5842. Min Range: -4.5842

Max Act: 2.7379. Min Act: -0.0000

Data Index: 1390551 (Python Code)

Max Activating Token Index: 727

Text #9

Max Range: 4.5842. Min Range: -4.5842

Max Act: 2.6596. Min Act: -0.0000

Data Index: 1363388 (Python Code)

Max Activating Token Index: 893

Text #10

Max Range: 4.5842. Min Range: -4.5842

Max Act: 2.6049. Min Act: -0.0000

Data Index: 1391298 (Python Code)

Max Activating Token Index: 466

Text #11

Max Range: 4.5842. Min Range: -4.5842

Max Act: 2.4722. Min Act: -0.0000

Data Index: 1464977 (Python Code)

Max Activating Token Index: 706

Text #12

Max Range: 4.5842. Min Range: -4.5842

Max Act: 2.5649. Min Act: -0.0000

Data Index: 1558692 (Python Code)

Max Activating Token Index: 570

Text #13

Max Range: 4.5842. Min Range: -4.5842

Max Act: 2.5322. Min Act: -0.0000

Data Index: 1462655 (Python Code)

Max Activating Token Index: 801

Text #14

Max Range: 4.5842. Min Range: -4.5842

Max Act: 2.6605. Min Act: -0.0000

Data Index: 1589172 (Python Code)

Max Activating Token Index: 448

Text #15

Max Range: 4.5842. Min Range: -4.5842

Max Act: 2.5116. Min Act: -0.0000

Data Index: 1439423 (Python Code)

Max Activating Token Index: 713

Text #16

Max Range: 4.5842. Min Range: -4.5842

Max Act: 2.6170. Min Act: -0.0000

Data Index: 1582765 (Python Code)

Max Activating Token Index: 102

Text #17

Max Range: 4.5842. Min Range: -4.5842

Max Act: 2.4946. Min Act: -0.0000

Data Index: 1372117 (Python Code)

Max Activating Token Index: 381

Text #18

Max Range: 4.5842. Min Range: -4.5842

Max Act: 2.7252. Min Act: -0.0000

Data Index: 1372767 (Python Code)

Max Activating Token Index: 216

Text #19

Max Range: 4.5842. Min Range: -4.5842

Max Act: 2.4528. Min Act: -0.0000

Data Index: 1513064 (Python Code)

Max Activating Token Index: 447