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

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

Neuron 2471 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0444. Min Range: -1.0444

Max Act: 1.0444. Min Act: -0.0001

Data Index: 193057 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7852. Min Act: -0.0001

Data Index: 115265 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.9444. Min Act: -0.0001

Data Index: 961175 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 1.0444. Min Range: -1.0444

Max Act: 1.0319. Min Act: -0.0001

Data Index: 503330 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.9948. Min Act: -0.0001

Data Index: 874892 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.9350. Min Act: -0.0001

Data Index: 1153258 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.8634. Min Act: -0.0001

Data Index: 1264614 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.9453. Min Act: -0.0001

Data Index: 783980 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.9036. Min Act: -0.0001

Data Index: 714474 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.9162. Min Act: -0.0001

Data Index: 375854 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.8981. Min Act: -0.0001

Data Index: 232436 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.9026. Min Act: -0.0001

Data Index: 1293328 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7200. Min Act: -0.0001

Data Index: 847805 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.8260. Min Act: -0.0001

Data Index: 789068 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.8386. Min Act: -0.0001

Data Index: 1153950 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.8133. Min Act: -0.0001

Data Index: 887191 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.9567. Min Act: -0.0001

Data Index: 500761 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.8423. Min Act: -0.0001

Data Index: 658652 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.8011. Min Act: -0.0001

Data Index: 1062781 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.8285. Min Act: -0.0001

Data Index: 969409 (C4 (Web Text))

Max Activating Token Index: 672