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

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

Neuron 2697 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5668. Min Range: -4.5668

Max Act: 4.5668. Min Act: -0.0000

Data Index: 1552189 (Python Code)

Max Activating Token Index: 117

Text #1

Max Range: 4.5668. Min Range: -4.5668

Max Act: 4.4448. Min Act: -0.0000

Data Index: 151287 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 4.5668. Min Range: -4.5668

Max Act: 4.5552. Min Act: -0.0000

Data Index: 1578935 (Python Code)

Max Activating Token Index: 292

Text #3

Max Range: 4.5668. Min Range: -4.5668

Max Act: 3.6705. Min Act: -0.0000

Data Index: 1650490 (Python Code)

Max Activating Token Index: 213

Text #4

Max Range: 4.5668. Min Range: -4.5668

Max Act: 4.0777. Min Act: -0.0000

Data Index: 1393398 (Python Code)

Max Activating Token Index: 64

Text #5

Max Range: 4.5668. Min Range: -4.5668

Max Act: 3.8792. Min Act: -0.0000

Data Index: 950615 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 4.5668. Min Range: -4.5668

Max Act: 3.8012. Min Act: -0.0000

Data Index: 1496593 (Python Code)

Max Activating Token Index: 227

Text #7

Max Range: 4.5668. Min Range: -4.5668

Max Act: 3.7537. Min Act: -0.0001

Data Index: 1448906 (Python Code)

Max Activating Token Index: 356

Text #8

Max Range: 4.5668. Min Range: -4.5668

Max Act: 3.8615. Min Act: -0.0000

Data Index: 1620886 (Python Code)

Max Activating Token Index: 155

Text #9

Max Range: 4.5668. Min Range: -4.5668

Max Act: 3.4817. Min Act: -0.0000

Data Index: 450475 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 4.5668. Min Range: -4.5668

Max Act: 3.6824. Min Act: -0.0000

Data Index: 1477504 (Python Code)

Max Activating Token Index: 361

Text #11

Max Range: 4.5668. Min Range: -4.5668

Max Act: 3.4515. Min Act: -0.0000

Data Index: 1383216 (Python Code)

Max Activating Token Index: 354

Text #12

Max Range: 4.5668. Min Range: -4.5668

Max Act: 3.5893. Min Act: -0.0000

Data Index: 1426681 (Python Code)

Max Activating Token Index: 644

Text #13

Max Range: 4.5668. Min Range: -4.5668

Max Act: 3.5754. Min Act: -0.0000

Data Index: 1453727 (Python Code)

Max Activating Token Index: 264

Text #14

Max Range: 4.5668. Min Range: -4.5668

Max Act: 3.5841. Min Act: -0.0000

Data Index: 1612303 (Python Code)

Max Activating Token Index: 79

Text #15

Max Range: 4.5668. Min Range: -4.5668

Max Act: 3.6057. Min Act: -0.0000

Data Index: 1555919 (Python Code)

Max Activating Token Index: 566

Text #16

Max Range: 4.5668. Min Range: -4.5668

Max Act: 3.5017. Min Act: -0.0000

Data Index: 649862 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 4.5668. Min Range: -4.5668

Max Act: 3.4170. Min Act: -0.0000

Data Index: 1478836 (Python Code)

Max Activating Token Index: 88

Text #18

Max Range: 4.5668. Min Range: -4.5668

Max Act: 3.4930. Min Act: -0.0000

Data Index: 1602210 (Python Code)

Max Activating Token Index: 259

Text #19

Max Range: 4.5668. Min Range: -4.5668

Max Act: 3.3227. Min Act: -0.0000

Data Index: 1522521 (Python Code)

Max Activating Token Index: 179