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

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

Neuron 51 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9429. Min Range: -3.9429

Max Act: 3.9170. Min Act: -0.0001

Data Index: 1152998 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 3.9429. Min Range: -3.9429

Max Act: 3.9429. Min Act: -0.0001

Data Index: 1323729 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 3.9429. Min Range: -3.9429

Max Act: 3.7670. Min Act: -0.0001

Data Index: 3698 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 3.9429. Min Range: -3.9429

Max Act: 3.4520. Min Act: -0.0001

Data Index: 335847 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 3.9429. Min Range: -3.9429

Max Act: 3.4401. Min Act: -0.0001

Data Index: 441517 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 3.9429. Min Range: -3.9429

Max Act: 3.5382. Min Act: -0.0001

Data Index: 1045170 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 3.9429. Min Range: -3.9429

Max Act: 3.3243. Min Act: -0.0001

Data Index: 15550 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 3.9429. Min Range: -3.9429

Max Act: 3.1722. Min Act: -0.0001

Data Index: 1124446 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 3.9429. Min Range: -3.9429

Max Act: 3.4140. Min Act: -0.0001

Data Index: 89081 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 3.9429. Min Range: -3.9429

Max Act: 3.3896. Min Act: -0.0001

Data Index: 94515 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 3.9429. Min Range: -3.9429

Max Act: 3.1621. Min Act: -0.0001

Data Index: 2464 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 3.9429. Min Range: -3.9429

Max Act: 3.1310. Min Act: -0.0001

Data Index: 1119510 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 3.9429. Min Range: -3.9429

Max Act: 3.1289. Min Act: -0.0001

Data Index: 659500 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 3.9429. Min Range: -3.9429

Max Act: 2.9610. Min Act: -0.0001

Data Index: 338165 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 3.9429. Min Range: -3.9429

Max Act: 3.0996. Min Act: -0.0001

Data Index: 1223994 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 3.9429. Min Range: -3.9429

Max Act: 3.2202. Min Act: -0.0001

Data Index: 569585 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 3.9429. Min Range: -3.9429

Max Act: 3.1793. Min Act: -0.0001

Data Index: 1332726 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 3.9429. Min Range: -3.9429

Max Act: 3.0031. Min Act: -0.0001

Data Index: 1217473 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 3.9429. Min Range: -3.9429

Max Act: 2.8017. Min Act: -0.0001

Data Index: 400399 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 3.9429. Min Range: -3.9429

Max Act: 2.8079. Min Act: -0.0001

Data Index: 672151 (C4 (Web Text))

Max Activating Token Index: 947