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

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

Neuron 5882 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: 3.2417. Min Range: -3.2417

Max Act: 3.2417. Min Act: -0.0000

Data Index: 771504 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.9161. Min Act: -0.0000

Data Index: 389848 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.6405. Min Act: -0.0000

Data Index: 1451799 (Python Code)

Max Activating Token Index: 248

Text #3

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.7207. Min Act: -0.0000

Data Index: 1593765 (Python Code)

Max Activating Token Index: 286

Text #4

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.4950. Min Act: -0.0000

Data Index: 1474504 (Python Code)

Max Activating Token Index: 402

Text #5

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.7409. Min Act: -0.0000

Data Index: 1030000 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.3328. Min Act: -0.0000

Data Index: 1274132 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.5306. Min Act: -0.0000

Data Index: 1464086 (Python Code)

Max Activating Token Index: 340

Text #8

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.5222. Min Act: -0.0000

Data Index: 1518520 (Python Code)

Max Activating Token Index: 781

Text #9

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.5343. Min Act: -0.0000

Data Index: 1653772 (Python Code)

Max Activating Token Index: 784

Text #10

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.1550. Min Act: -0.0000

Data Index: 1058491 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.3416. Min Act: 0.0000

Data Index: 1612678 (Python Code)

Max Activating Token Index: 102

Text #12

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.2115. Min Act: -0.0000

Data Index: 1555424 (Python Code)

Max Activating Token Index: 770

Text #13

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.0954. Min Act: 0.0000

Data Index: 1507552 (Python Code)

Max Activating Token Index: 819

Text #14

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.0855. Min Act: -0.0000

Data Index: 1502560 (Python Code)

Max Activating Token Index: 751

Text #15

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.1758. Min Act: 0.0000

Data Index: 1170445 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.0764. Min Act: -0.0000

Data Index: 1614932 (Python Code)

Max Activating Token Index: 495

Text #17

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.1369. Min Act: -0.0000

Data Index: 1419738 (Python Code)

Max Activating Token Index: 633

Text #18

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.0249. Min Act: -0.0000

Data Index: 1417837 (Python Code)

Max Activating Token Index: 805

Text #19

Max Range: 3.2417. Min Range: -3.2417

Max Act: 2.1204. Min Act: -0.0000

Data Index: 1581085 (Python Code)

Max Activating Token Index: 99