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

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

Neuron 3357 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.8332. Min Act: -0.0000

Data Index: 541988 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.6037. Min Act: -0.0000

Data Index: 587226 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.6066. Min Act: -0.0000

Data Index: 146829 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.5395. Min Act: -0.0000

Data Index: 48912 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.5605. Min Act: -0.0000

Data Index: 605321 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.5410. Min Act: -0.0000

Data Index: 147037 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.5352. Min Act: -0.0000

Data Index: 407570 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.5297. Min Act: -0.0000

Data Index: 996544 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.5262. Min Act: -0.0000

Data Index: 295305 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1117135 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.4909. Min Act: -0.0000

Data Index: 598084 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.5206. Min Act: -0.0000

Data Index: 330269 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1075311 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.4552. Min Act: -0.0000

Data Index: 303835 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.4685. Min Act: -0.0000

Data Index: 1261505 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.4442. Min Act: -0.0000

Data Index: 1459155 (Python Code)

Max Activating Token Index: 914

Text #16

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.4750. Min Act: -0.0000

Data Index: 1335798 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.4627. Min Act: -0.0000

Data Index: 813631 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.4609. Min Act: -0.0000

Data Index: 269274 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.8332. Min Range: -0.8332

Max Act: 0.4650. Min Act: -0.0000

Data Index: 56463 (C4 (Web Text))

Max Activating Token Index: 917