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

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

Neuron 4089 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.4456. Min Act: -0.0001

Data Index: 573108 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3368. Min Act: -0.0001

Data Index: 572631 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2961. Min Act: -0.0001

Data Index: 1389553 (Python Code)

Max Activating Token Index: 518

Text #3

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3038. Min Act: -0.0001

Data Index: 122013 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2912. Min Act: -0.0001

Data Index: 1019178 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2707. Min Act: -0.0001

Data Index: 1079818 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2808. Min Act: -0.0001

Data Index: 976254 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.1994. Min Act: -0.0001

Data Index: 882013 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2583. Min Act: -0.0001

Data Index: 1524508 (Python Code)

Max Activating Token Index: 649

Text #9

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2805. Min Act: -0.0001

Data Index: 322527 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2573. Min Act: -0.0001

Data Index: 928639 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2428. Min Act: -0.0001

Data Index: 960223 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2708. Min Act: -0.0001

Data Index: 1499154 (Python Code)

Max Activating Token Index: 974

Text #13

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2504. Min Act: -0.0001

Data Index: 338366 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2766. Min Act: -0.0001

Data Index: 331553 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2561. Min Act: -0.0001

Data Index: 291877 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2597. Min Act: -0.0001

Data Index: 1005516 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2584. Min Act: -0.0001

Data Index: 745821 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2059. Min Act: -0.0001

Data Index: 55916 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2337. Min Act: -0.0001

Data Index: 680876 (C4 (Web Text))

Max Activating Token Index: 138