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

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

Neuron 1367 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: 1.1367. Min Range: -1.1367

Max Act: 1.1367. Min Act: -0.0000

Data Index: 212961 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.9896. Min Act: -0.0000

Data Index: 971372 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 1.1367. Min Range: -1.1367

Max Act: 1.0298. Min Act: -0.0000

Data Index: 343662 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.8892. Min Act: -0.0000

Data Index: 1020755 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.8747. Min Act: -0.0000

Data Index: 309795 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.7993. Min Act: -0.0000

Data Index: 285505 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.8699. Min Act: -0.0000

Data Index: 1017436 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.8243. Min Act: -0.0000

Data Index: 105399 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.8280. Min Act: -0.0000

Data Index: 43248 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.8005. Min Act: -0.0000

Data Index: 1027894 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.8040. Min Act: -0.0000

Data Index: 793224 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.7579. Min Act: -0.0000

Data Index: 903394 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.6983. Min Act: -0.0000

Data Index: 926211 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.7560. Min Act: -0.0000

Data Index: 194294 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.7255. Min Act: -0.0000

Data Index: 284326 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.7254. Min Act: -0.0000

Data Index: 487823 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.7103. Min Act: -0.0000

Data Index: 675530 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.7411. Min Act: -0.0000

Data Index: 349578 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.6951. Min Act: -0.0000

Data Index: 863042 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 1.1367. Min Range: -1.1367

Max Act: 0.6879. Min Act: -0.0000

Data Index: 1313589 (C4 (Web Text))

Max Activating Token Index: 214