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

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

Neuron 1365 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.9453. Min Act: -0.0000

Data Index: 754464 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.9324. Min Act: -0.0000

Data Index: 529196 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.8775. Min Act: -0.0000

Data Index: 593230 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1562288 (Python Code)

Max Activating Token Index: 311

Text #4

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.8550. Min Act: -0.0001

Data Index: 1217936 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1125163 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1063934 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.7335. Min Act: -0.0000

Data Index: 753996 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.7212. Min Act: -0.0000

Data Index: 1106330 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6981. Min Act: -0.0000

Data Index: 866853 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.7759. Min Act: -0.0000

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.7250. Min Act: -0.0000

Data Index: 1580739 (Python Code)

Max Activating Token Index: 908

Text #12

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.7078. Min Act: -0.0000

Data Index: 1417777 (Python Code)

Max Activating Token Index: 223

Text #13

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.7163. Min Act: -0.0000

Data Index: 310683 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6935. Min Act: -0.0001

Data Index: 363551 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6769. Min Act: -0.0000

Data Index: 1277654 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6798. Min Act: -0.0000

Data Index: 695530 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6659. Min Act: -0.0000

Data Index: 1424427 (Python Code)

Max Activating Token Index: 455

Text #18

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6601. Min Act: -0.0000

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6283. Min Act: -0.0000

Data Index: 336227 (C4 (Web Text))

Max Activating Token Index: 771