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

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

Neuron 5412 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: 2.9588. Min Range: -2.9588

Max Act: 2.9588. Min Act: -0.0000

Data Index: 1653038 (Python Code)

Max Activating Token Index: 472

Text #1

Max Range: 2.9588. Min Range: -2.9588

Max Act: 2.8700. Min Act: -0.0000

Data Index: 1431270 (Python Code)

Max Activating Token Index: 835

Text #2

Max Range: 2.9588. Min Range: -2.9588

Max Act: 2.8709. Min Act: -0.0000

Data Index: 1440516 (Python Code)

Max Activating Token Index: 373

Text #3

Max Range: 2.9588. Min Range: -2.9588

Max Act: 2.5066. Min Act: -0.0000

Data Index: 1584821 (Python Code)

Max Activating Token Index: 85

Text #4

Max Range: 2.9588. Min Range: -2.9588

Max Act: 1.9570. Min Act: -0.0000

Data Index: 1583284 (Python Code)

Max Activating Token Index: 585

Text #5

Max Range: 2.9588. Min Range: -2.9588

Max Act: 1.6994. Min Act: -0.0000

Data Index: 1492549 (Python Code)

Max Activating Token Index: 726

Text #6

Max Range: 2.9588. Min Range: -2.9588

Max Act: 1.6939. Min Act: -0.0000

Data Index: 681680 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 2.9588. Min Range: -2.9588

Max Act: 1.4319. Min Act: -0.0000

Data Index: 1527598 (Python Code)

Max Activating Token Index: 189

Text #8

Max Range: 2.9588. Min Range: -2.9588

Max Act: 1.4789. Min Act: -0.0000

Data Index: 1438489 (Python Code)

Max Activating Token Index: 349

Text #9

Max Range: 2.9588. Min Range: -2.9588

Max Act: 1.5311. Min Act: -0.0000

Data Index: 1438938 (Python Code)

Max Activating Token Index: 249

Text #10

Max Range: 2.9588. Min Range: -2.9588

Max Act: 1.4014. Min Act: -0.0000

Data Index: 1640547 (Python Code)

Max Activating Token Index: 943

Text #11

Max Range: 2.9588. Min Range: -2.9588

Max Act: 1.2466. Min Act: -0.0000

Data Index: 1568205 (Python Code)

Max Activating Token Index: 100

Text #12

Max Range: 2.9588. Min Range: -2.9588

Max Act: 1.3196. Min Act: -0.0000

Data Index: 786763 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 2.9588. Min Range: -2.9588

Max Act: 1.1669. Min Act: -0.0000

Data Index: 1050950 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 2.9588. Min Range: -2.9588

Max Act: 1.3271. Min Act: -0.0000

Data Index: 1600145 (Python Code)

Max Activating Token Index: 62

Text #15

Max Range: 2.9588. Min Range: -2.9588

Max Act: 1.2359. Min Act: -0.0000

Data Index: 1099529 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 2.9588. Min Range: -2.9588

Max Act: 1.2278. Min Act: -0.0000

Data Index: 1583667 (Python Code)

Max Activating Token Index: 305

Text #17

Max Range: 2.9588. Min Range: -2.9588

Max Act: 1.1463. Min Act: -0.0000

Data Index: 42221 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 2.9588. Min Range: -2.9588

Max Act: 1.1592. Min Act: -0.0000

Data Index: 569002 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 2.9588. Min Range: -2.9588

Max Act: 1.2080. Min Act: -0.0000

Data Index: 1515616 (Python Code)

Max Activating Token Index: 765