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

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

Neuron 292 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.5386. Min Act: -0.0000

Data Index: 928371 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.5279. Min Act: -0.0000

Data Index: 1545404 (Python Code)

Max Activating Token Index: 717

Text #2

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.5350. Min Act: -0.0000

Data Index: 1440812 (Python Code)

Max Activating Token Index: 657

Text #3

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4967. Min Act: -0.0000

Data Index: 1574075 (Python Code)

Max Activating Token Index: 670

Text #4

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.5103. Min Act: -0.0000

Data Index: 1638935 (Python Code)

Max Activating Token Index: 432

Text #5

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.5181. Min Act: -0.0000

Data Index: 810922 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4935. Min Act: -0.0000

Data Index: 936315 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1532507 (Python Code)

Max Activating Token Index: 441

Text #8

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1512885 (Python Code)

Max Activating Token Index: 808

Text #9

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1496436 (Python Code)

Max Activating Token Index: 136

Text #10

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1479164 (Python Code)

Max Activating Token Index: 617

Text #11

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1514035 (Python Code)

Max Activating Token Index: 329

Text #12

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4652. Min Act: -0.0000

Data Index: 809468 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4465. Min Act: -0.0000

Data Index: 1557598 (Python Code)

Max Activating Token Index: 584

Text #14

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4441. Min Act: -0.0000

Data Index: 1478845 (Python Code)

Max Activating Token Index: 526

Text #15

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1440300 (Python Code)

Max Activating Token Index: 207

Text #16

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4126. Min Act: -0.0000

Data Index: 1572460 (Python Code)

Max Activating Token Index: 177

Text #17

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1516875 (Python Code)

Max Activating Token Index: 54

Text #18

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4458. Min Act: -0.0000

Data Index: 1407291 (Python Code)

Max Activating Token Index: 832

Text #19

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1630005 (Python Code)

Max Activating Token Index: 292