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

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

Neuron 2491 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: 0.8265. Min Range: -0.8265

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1641636 (Python Code)

Max Activating Token Index: 676

Text #1

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.7650. Min Act: -0.0000

Data Index: 97618 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.7277. Min Act: -0.0000

Data Index: 604099 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.7231. Min Act: -0.0000

Data Index: 187737 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6948. Min Act: -0.0000

Data Index: 868090 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6410. Min Act: -0.0000

Data Index: 1518301 (Python Code)

Max Activating Token Index: 706

Text #6

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6842. Min Act: -0.0000

Data Index: 1640754 (Python Code)

Max Activating Token Index: 458

Text #7

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6487. Min Act: -0.0000

Data Index: 1556909 (Python Code)

Max Activating Token Index: 368

Text #8

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6895. Min Act: -0.0000

Data Index: 787215 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6825. Min Act: -0.0000

Data Index: 614689 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6578. Min Act: -0.0000

Data Index: 1485444 (Python Code)

Max Activating Token Index: 506

Text #11

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6444. Min Act: -0.0000

Data Index: 1649292 (Python Code)

Max Activating Token Index: 246

Text #12

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6045. Min Act: -0.0000

Data Index: 737069 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1591909 (Python Code)

Max Activating Token Index: 774

Text #14

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6253. Min Act: -0.0000

Data Index: 1544931 (Python Code)

Max Activating Token Index: 476

Text #15

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1389960 (Python Code)

Max Activating Token Index: 374

Text #16

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6417. Min Act: -0.0000

Data Index: 1066471 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1548164 (Python Code)

Max Activating Token Index: 585

Text #18

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6740. Min Act: -0.0000

Data Index: 1605439 (Python Code)

Max Activating Token Index: 761

Text #19

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.5893. Min Act: -0.0000

Data Index: 92108 (C4 (Web Text))

Max Activating Token Index: 622