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

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

Neuron 3395 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2543. Min Range: -1.2543

Max Act: 1.2346. Min Act: -0.0000

Data Index: 133857 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 1.2543. Min Range: -1.2543

Max Act: 1.2543. Min Act: -0.0000

Data Index: 150399 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 1.2543. Min Range: -1.2543

Max Act: 1.2206. Min Act: -0.0000

Data Index: 815232 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 1.2543. Min Range: -1.2543

Max Act: 0.9372. Min Act: -0.0000

Data Index: 1648702 (Python Code)

Max Activating Token Index: 341

Text #4

Max Range: 1.2543. Min Range: -1.2543

Max Act: 0.8890. Min Act: -0.0000

Data Index: 1396486 (Python Code)

Max Activating Token Index: 968

Text #5

Max Range: 1.2543. Min Range: -1.2543

Max Act: 0.8423. Min Act: -0.0000

Data Index: 130541 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 1.2543. Min Range: -1.2543

Max Act: 0.9175. Min Act: -0.0000

Data Index: 1512592 (Python Code)

Max Activating Token Index: 620

Text #7

Max Range: 1.2543. Min Range: -1.2543

Max Act: 0.8665. Min Act: -0.0000

Data Index: 811954 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 1.2543. Min Range: -1.2543

Max Act: 0.8253. Min Act: -0.0000

Data Index: 228069 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 1.2543. Min Range: -1.2543

Max Act: 0.8394. Min Act: -0.0000

Data Index: 72276 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 1.2543. Min Range: -1.2543

Max Act: 0.8392. Min Act: -0.0000

Data Index: 589071 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 1.2543. Min Range: -1.2543

Max Act: 0.8352. Min Act: -0.0000

Data Index: 1068890 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 1.2543. Min Range: -1.2543

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1512934 (Python Code)

Max Activating Token Index: 412

Text #13

Max Range: 1.2543. Min Range: -1.2543

Max Act: 0.7475. Min Act: -0.0000

Data Index: 1273770 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 1.2543. Min Range: -1.2543

Max Act: 0.7545. Min Act: -0.0000

Data Index: 1484330 (Python Code)

Max Activating Token Index: 1013

Text #15

Max Range: 1.2543. Min Range: -1.2543

Max Act: 0.7523. Min Act: -0.0000

Data Index: 978929 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 1.2543. Min Range: -1.2543

Max Act: 0.7497. Min Act: -0.0000

Data Index: 1341306 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 1.2543. Min Range: -1.2543

Max Act: 0.7290. Min Act: -0.0000

Data Index: 914116 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 1.2543. Min Range: -1.2543

Max Act: 0.7567. Min Act: -0.0000

Data Index: 199341 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 1.2543. Min Range: -1.2543

Max Act: 0.7527. Min Act: -0.0000

Data Index: 1365466 (Python Code)

Max Activating Token Index: 978