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

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

Neuron 5087 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.4564. Min Act: -0.0000

Data Index: 1001274 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.4128. Min Act: -0.0001

Data Index: 494668 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3937. Min Act: -0.0000

Data Index: 253785 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3657. Min Act: -0.0000

Data Index: 854530 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3775. Min Act: -0.0000

Data Index: 596743 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3329. Min Act: -0.0001

Data Index: 1126619 (C4 (Web Text))

Max Activating Token Index: 791

Text #6

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3452. Min Act: -0.0000

Data Index: 242120 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3558. Min Act: -0.0000

Data Index: 953632 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3751. Min Act: -0.0001

Data Index: 550312 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3379. Min Act: -0.0000

Data Index: 82854 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3761. Min Act: -0.0000

Data Index: 794000 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3569. Min Act: -0.0000

Data Index: 552424 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3265. Min Act: -0.0000

Data Index: 1249044 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3323. Min Act: -0.0001

Data Index: 1555790 (Python Code)

Max Activating Token Index: 77

Text #14

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3100. Min Act: -0.0000

Data Index: 780333 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3334. Min Act: -0.0001

Data Index: 941299 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1548503 (Python Code)

Max Activating Token Index: 7

Text #17

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3082. Min Act: -0.0000

Data Index: 671035 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3275. Min Act: -0.0001

Data Index: 1467696 (Python Code)

Max Activating Token Index: 149

Text #19

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3265. Min Act: -0.0000

Data Index: 802035 (C4 (Web Text))

Max Activating Token Index: 935