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

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

Neuron 5208 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6839. Min Range: -0.6839

Max Act: 0.6839. Min Act: -0.0000

Data Index: 1180830 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.6839. Min Range: -0.6839

Max Act: 0.5424. Min Act: -0.0000

Data Index: 295606 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.6839. Min Range: -0.6839

Max Act: 0.5336. Min Act: -0.0000

Data Index: 878655 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 0.6839. Min Range: -0.6839

Max Act: 0.5330. Min Act: -0.0000

Data Index: 436600 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.6839. Min Range: -0.6839

Max Act: 0.5708. Min Act: -0.0000

Data Index: 471897 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.6839. Min Range: -0.6839

Max Act: 0.4366. Min Act: -0.0000

Data Index: 233822 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.6839. Min Range: -0.6839

Max Act: 0.4683. Min Act: -0.0000

Data Index: 1257071 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.6839. Min Range: -0.6839

Max Act: 0.4352. Min Act: -0.0000

Data Index: 789505 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 0.6839. Min Range: -0.6839

Max Act: 0.4158. Min Act: -0.0000

Data Index: 668257 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.6839. Min Range: -0.6839

Max Act: 0.4054. Min Act: -0.0000

Data Index: 1478768 (Python Code)

Max Activating Token Index: 395

Text #10

Max Range: 0.6839. Min Range: -0.6839

Max Act: 0.4434. Min Act: -0.0000

Data Index: 277655 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 0.6839. Min Range: -0.6839

Max Act: 0.4089. Min Act: -0.0000

Data Index: 577487 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.6839. Min Range: -0.6839

Max Act: 0.3929. Min Act: -0.0000

Data Index: 1396180 (Python Code)

Max Activating Token Index: 770

Text #13

Max Range: 0.6839. Min Range: -0.6839

Max Act: 0.3795. Min Act: -0.0000

Data Index: 1267585 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 0.6839. Min Range: -0.6839

Max Act: 0.3869. Min Act: -0.0000

Data Index: 867635 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.6839. Min Range: -0.6839

Max Act: 0.3588. Min Act: -0.0000

Data Index: 278334 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.6839. Min Range: -0.6839

Max Act: 0.3495. Min Act: -0.0000

Data Index: 1536317 (Python Code)

Max Activating Token Index: 333

Text #17

Max Range: 0.6839. Min Range: -0.6839

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1363077 (Python Code)

Max Activating Token Index: 554

Text #18

Max Range: 0.6839. Min Range: -0.6839

Max Act: 0.3494. Min Act: -0.0000

Data Index: 1447963 (Python Code)

Max Activating Token Index: 876

Text #19

Max Range: 0.6839. Min Range: -0.6839

Max Act: 0.3283. Min Act: -0.0000

Data Index: 93100 (C4 (Web Text))

Max Activating Token Index: 263