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

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

Neuron 4813 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.6379. Min Act: -0.0000

Data Index: 1194996 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.4267. Min Act: -0.0000

Data Index: 368396 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.5035. Min Act: -0.0000

Data Index: 1071180 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.5450. Min Act: -0.0000

Data Index: 731935 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.4875. Min Act: -0.0000

Data Index: 519578 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.3889. Min Act: -0.0000

Data Index: 29944 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.3568. Min Act: -0.0000

Data Index: 540879 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.2416. Min Act: -0.0000

Data Index: 832503 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.2933. Min Act: -0.0000

Data Index: 1871 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.4510. Min Act: -0.0000

Data Index: 1114823 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.1381. Min Act: -0.0000

Data Index: 53095 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.1168. Min Act: -0.0000

Data Index: 827831 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.0975. Min Act: -0.0000

Data Index: 337537 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.1017. Min Act: -0.0000

Data Index: 1215299 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.0803. Min Act: -0.0000

Data Index: 351139 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.1333. Min Act: -0.0000

Data Index: 493052 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.0061. Min Act: -0.0000

Data Index: 17761 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.0642. Min Act: -0.0000

Data Index: 694832 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.1832. Min Act: -0.0000

Data Index: 963065 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 1.6379. Min Range: -1.6379

Max Act: 1.0505. Min Act: -0.0000

Data Index: 754072 (C4 (Web Text))

Max Activating Token Index: 467