Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1419 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.5056. Min Range: -4.5056

Max Act: 4.5056. Min Act: -0.0000

Data Index: 1419052 (Python Code)

Max Activating Token Index: 789

Text #1

Max Range: 4.5056. Min Range: -4.5056

Max Act: 4.0389. Min Act: -0.0000

Data Index: 1514617 (Python Code)

Max Activating Token Index: 451

Text #2

Max Range: 4.5056. Min Range: -4.5056

Max Act: 3.2463. Min Act: -0.0001

Data Index: 1646498 (Python Code)

Max Activating Token Index: 291

Text #3

Max Range: 4.5056. Min Range: -4.5056

Max Act: 3.2099. Min Act: -0.0001

Data Index: 1566492 (Python Code)

Max Activating Token Index: 503

Text #4

Max Range: 4.5056. Min Range: -4.5056

Max Act: 3.0763. Min Act: -0.0001

Data Index: 1559292 (Python Code)

Max Activating Token Index: 461

Text #5

Max Range: 4.5056. Min Range: -4.5056

Max Act: 3.1316. Min Act: -0.0000

Data Index: 1522964 (Python Code)

Max Activating Token Index: 312

Text #6

Max Range: 4.5056. Min Range: -4.5056

Max Act: 2.9979. Min Act: -0.0001

Data Index: 1455755 (Python Code)

Max Activating Token Index: 113

Text #7

Max Range: 4.5056. Min Range: -4.5056

Max Act: 3.2147. Min Act: -0.0001

Data Index: 1490539 (Python Code)

Max Activating Token Index: 351

Text #8

Max Range: 4.5056. Min Range: -4.5056

Max Act: 3.1644. Min Act: -0.0001

Data Index: 1638443 (Python Code)

Max Activating Token Index: 621

Text #9

Max Range: 4.5056. Min Range: -4.5056

Max Act: 2.7836. Min Act: -0.0001

Data Index: 1468078 (Python Code)

Max Activating Token Index: 134

Text #10

Max Range: 4.5056. Min Range: -4.5056

Max Act: 2.7626. Min Act: -0.0000

Data Index: 1644092 (Python Code)

Max Activating Token Index: 105

Text #11

Max Range: 4.5056. Min Range: -4.5056

Max Act: 2.3268. Min Act: -0.0001

Data Index: 1555391 (Python Code)

Max Activating Token Index: 369

Text #12

Max Range: 4.5056. Min Range: -4.5056

Max Act: 2.7054. Min Act: -0.0000

Data Index: 1537377 (Python Code)

Max Activating Token Index: 471

Text #13

Max Range: 4.5056. Min Range: -4.5056

Max Act: 2.6583. Min Act: -0.0000

Data Index: 1179386 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 4.5056. Min Range: -4.5056

Max Act: 2.7777. Min Act: -0.0001

Data Index: 1631876 (Python Code)

Max Activating Token Index: 279

Text #15

Max Range: 4.5056. Min Range: -4.5056

Max Act: 2.6287. Min Act: -0.0001

Data Index: 1407988 (Python Code)

Max Activating Token Index: 248

Text #16

Max Range: 4.5056. Min Range: -4.5056

Max Act: 2.4827. Min Act: -0.0001

Data Index: 870986 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 4.5056. Min Range: -4.5056

Max Act: 2.5896. Min Act: -0.0001

Data Index: 1372702 (Python Code)

Max Activating Token Index: 386

Text #18

Max Range: 4.5056. Min Range: -4.5056

Max Act: 2.8583. Min Act: -0.0001

Data Index: 1408829 (Python Code)

Max Activating Token Index: 667

Text #19

Max Range: 4.5056. Min Range: -4.5056

Max Act: 2.6738. Min Act: -0.0000

Data Index: 1515042 (Python Code)

Max Activating Token Index: 171