Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1214 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0409. Min Act: -0.0003

Data Index: 23193 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0396. Min Act: -0.0003

Data Index: 12609 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0374. Min Act: -0.0003

Data Index: 1134335 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0364. Min Act: -0.0003

Data Index: 295942 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0361. Min Act: -0.0004

Data Index: 1238989 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0356. Min Act: -0.0003

Data Index: 1233688 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0356. Min Act: -0.0003

Data Index: 843601 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0361. Min Act: -0.0003

Data Index: 1118853 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0344. Min Act: -0.0004

Data Index: 1259500 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0333. Min Act: -0.0004

Data Index: 1102955 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0331. Min Act: -0.0003

Data Index: 787156 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0330. Min Act: -0.0002

Data Index: 325573 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0331. Min Act: -0.0003

Data Index: 303936 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0337. Min Act: -0.0003

Data Index: 829436 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0335. Min Act: -0.0003

Data Index: 1050219 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0326. Min Act: -0.0003

Data Index: 812768 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0335. Min Act: -0.0003

Data Index: 1124662 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0331. Min Act: -0.0003

Data Index: 583123 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0333. Min Act: -0.0003

Data Index: 752314 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0323. Min Act: -0.0004

Data Index: 1218301 (C4 (Web Text))

Max Activating Token Index: 615