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

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

Neuron 4288 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.3830. Min Act: -0.0000

Data Index: 1394051 (Python Code)

Max Activating Token Index: 858

Text #1

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.3305. Min Act: -0.0000

Data Index: 1473898 (Python Code)

Max Activating Token Index: 269

Text #2

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.3705. Min Act: -0.0000

Data Index: 1619354 (Python Code)

Max Activating Token Index: 909

Text #3

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.3320. Min Act: -0.0000

Data Index: 1594529 (Python Code)

Max Activating Token Index: 300

Text #4

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.2805. Min Act: -0.0000

Data Index: 1249096 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.3404. Min Act: -0.0000

Data Index: 1538027 (Python Code)

Max Activating Token Index: 779

Text #6

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.2357. Min Act: -0.0000

Data Index: 1538544 (Python Code)

Max Activating Token Index: 142

Text #7

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.2548. Min Act: -0.0000

Data Index: 1583065 (Python Code)

Max Activating Token Index: 63

Text #8

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.1674. Min Act: -0.0000

Data Index: 1536386 (Python Code)

Max Activating Token Index: 890

Text #9

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.2422. Min Act: -0.0000

Data Index: 1597618 (Python Code)

Max Activating Token Index: 510

Text #10

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.2745. Min Act: -0.0000

Data Index: 1362597 (Python Code)

Max Activating Token Index: 362

Text #11

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.1933. Min Act: -0.0000

Data Index: 1618640 (Python Code)

Max Activating Token Index: 43

Text #12

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.2207. Min Act: -0.0000

Data Index: 530412 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.2435. Min Act: -0.0000

Data Index: 1276274 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.2405. Min Act: -0.0000

Data Index: 640821 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.2380. Min Act: -0.0000

Data Index: 1506755 (Python Code)

Max Activating Token Index: 569

Text #16

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.2037. Min Act: -0.0000

Data Index: 418256 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.2394. Min Act: -0.0000

Data Index: 1519333 (Python Code)

Max Activating Token Index: 820

Text #18

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.1554. Min Act: -0.0000

Data Index: 1551161 (Python Code)

Max Activating Token Index: 91

Text #19

Max Range: 1.3830. Min Range: -1.3830

Max Act: 1.1742. Min Act: -0.0000

Data Index: 1063724 (C4 (Web Text))

Max Activating Token Index: 1014