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

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

Neuron 4599 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: 2.9204. Min Range: -2.9204

Max Act: 2.9204. Min Act: -0.0000

Data Index: 1414221 (Python Code)

Max Activating Token Index: 667

Text #1

Max Range: 2.9204. Min Range: -2.9204

Max Act: 2.7354. Min Act: -0.0000

Data Index: 1407283 (Python Code)

Max Activating Token Index: 534

Text #2

Max Range: 2.9204. Min Range: -2.9204

Max Act: 2.6714. Min Act: -0.0000

Data Index: 1392696 (Python Code)

Max Activating Token Index: 730

Text #3

Max Range: 2.9204. Min Range: -2.9204

Max Act: 2.6534. Min Act: -0.0000

Data Index: 1449310 (Python Code)

Max Activating Token Index: 637

Text #4

Max Range: 2.9204. Min Range: -2.9204

Max Act: 2.6346. Min Act: -0.0000

Data Index: 1615476 (Python Code)

Max Activating Token Index: 716

Text #5

Max Range: 2.9204. Min Range: -2.9204

Max Act: 2.4638. Min Act: -0.0000

Data Index: 1554339 (Python Code)

Max Activating Token Index: 539

Text #6

Max Range: 2.9204. Min Range: -2.9204

Max Act: 2.4417. Min Act: -0.0000

Data Index: 1374964 (Python Code)

Max Activating Token Index: 663

Text #7

Max Range: 2.9204. Min Range: -2.9204

Max Act: 2.5697. Min Act: -0.0000

Data Index: 1421018 (Python Code)

Max Activating Token Index: 790

Text #8

Max Range: 2.9204. Min Range: -2.9204

Max Act: 2.5588. Min Act: -0.0000

Data Index: 1387997 (Python Code)

Max Activating Token Index: 930

Text #9

Max Range: 2.9204. Min Range: -2.9204

Max Act: 2.4995. Min Act: -0.0000

Data Index: 1626492 (Python Code)

Max Activating Token Index: 108

Text #10

Max Range: 2.9204. Min Range: -2.9204

Max Act: 2.4944. Min Act: -0.0000

Data Index: 1654557 (Python Code)

Max Activating Token Index: 834

Text #11

Max Range: 2.9204. Min Range: -2.9204

Max Act: 2.5099. Min Act: -0.0000

Data Index: 1458672 (Python Code)

Max Activating Token Index: 768

Text #12

Max Range: 2.9204. Min Range: -2.9204

Max Act: 2.4154. Min Act: -0.0000

Data Index: 1472658 (Python Code)

Max Activating Token Index: 79

Text #13

Max Range: 2.9204. Min Range: -2.9204

Max Act: 2.3697. Min Act: -0.0000

Data Index: 1440506 (Python Code)

Max Activating Token Index: 877

Text #14

Max Range: 2.9204. Min Range: -2.9204

Max Act: 2.3466. Min Act: -0.0000

Data Index: 1360165 (Python Code)

Max Activating Token Index: 913

Text #15

Max Range: 2.9204. Min Range: -2.9204

Max Act: 2.3492. Min Act: -0.0000

Data Index: 1445987 (Python Code)

Max Activating Token Index: 203

Text #16

Max Range: 2.9204. Min Range: -2.9204

Max Act: 2.4445. Min Act: -0.0000

Data Index: 1183667 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 2.9204. Min Range: -2.9204

Max Act: 2.1970. Min Act: -0.0000

Data Index: 1530276 (Python Code)

Max Activating Token Index: 201

Text #18

Max Range: 2.9204. Min Range: -2.9204

Max Act: 2.1819. Min Act: -0.0000

Data Index: 1627698 (Python Code)

Max Activating Token Index: 442

Text #19

Max Range: 2.9204. Min Range: -2.9204

Max Act: 2.3345. Min Act: -0.0000

Data Index: 1557459 (Python Code)

Max Activating Token Index: 55