Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1447 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.8344. Min Range: -1.8344

Max Act: 1.8344. Min Act: -0.0001

Data Index: 143190 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 1.8344. Min Range: -1.8344

Max Act: 1.5338. Min Act: -0.0001

Data Index: 1138045 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 1.8344. Min Range: -1.8344

Max Act: 1.5788. Min Act: -0.0001

Data Index: 1239695 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 1.8344. Min Range: -1.8344

Max Act: 1.2482. Min Act: -0.0001

Data Index: 436041 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 1.8344. Min Range: -1.8344

Max Act: 1.4343. Min Act: -0.0001

Data Index: 38452 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 1.8344. Min Range: -1.8344

Max Act: 1.3828. Min Act: -0.0001

Data Index: 813584 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 1.8344. Min Range: -1.8344

Max Act: 1.1350. Min Act: -0.0001

Data Index: 50855 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 1.8344. Min Range: -1.8344

Max Act: 1.3173. Min Act: -0.0001

Data Index: 1084509 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 1.8344. Min Range: -1.8344

Max Act: 1.3142. Min Act: -0.0001

Data Index: 741477 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 1.8344. Min Range: -1.8344

Max Act: 1.3205. Min Act: -0.0001

Data Index: 88325 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 1.8344. Min Range: -1.8344

Max Act: 1.4091. Min Act: -0.0001

Data Index: 606119 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 1.8344. Min Range: -1.8344

Max Act: 1.2906. Min Act: -0.0001

Data Index: 730845 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 1.8344. Min Range: -1.8344

Max Act: 1.3643. Min Act: -0.0001

Data Index: 1053218 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 1.8344. Min Range: -1.8344

Max Act: 1.3224. Min Act: -0.0001

Data Index: 1223469 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 1.8344. Min Range: -1.8344

Max Act: 1.2994. Min Act: -0.0001

Data Index: 779499 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 1.8344. Min Range: -1.8344

Max Act: 1.1328. Min Act: -0.0001

Data Index: 542383 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 1.8344. Min Range: -1.8344

Max Act: 1.3497. Min Act: -0.0001

Data Index: 1146212 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 1.8344. Min Range: -1.8344

Max Act: 1.1961. Min Act: -0.0001

Data Index: 345033 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 1.8344. Min Range: -1.8344

Max Act: 1.2328. Min Act: -0.0001

Data Index: 462505 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 1.8344. Min Range: -1.8344

Max Act: 1.3530. Min Act: -0.0001

Data Index: 544102 (C4 (Web Text))

Max Activating Token Index: 949