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

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

Neuron 945 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: 3.0468. Min Range: -3.0468

Max Act: 3.0468. Min Act: -0.0001

Data Index: 17558 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.8374. Min Act: -0.0001

Data Index: 906949 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.4753. Min Act: -0.0001

Data Index: 646129 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.4146. Min Act: -0.0000

Data Index: 1335555 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.3807. Min Act: -0.0000

Data Index: 115604 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.2995. Min Act: -0.0000

Data Index: 801647 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 3.0468. Min Range: -3.0468

Max Act: 2.0703. Min Act: -0.0001

Data Index: 174566 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 3.0468. Min Range: -3.0468

Max Act: 1.5448. Min Act: -0.0000

Data Index: 1163884 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 3.0468. Min Range: -3.0468

Max Act: 1.8044. Min Act: -0.0001

Data Index: 245114 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 3.0468. Min Range: -3.0468

Max Act: 1.7073. Min Act: -0.0000

Data Index: 1273501 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 3.0468. Min Range: -3.0468

Max Act: 1.6611. Min Act: -0.0000

Data Index: 1272934 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 3.0468. Min Range: -3.0468

Max Act: 1.7190. Min Act: -0.0000

Data Index: 507325 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 3.0468. Min Range: -3.0468

Max Act: 1.5129. Min Act: -0.0000

Data Index: 359570 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 3.0468. Min Range: -3.0468

Max Act: 1.4921. Min Act: -0.0000

Data Index: 676162 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 3.0468. Min Range: -3.0468

Max Act: 1.5644. Min Act: -0.0000

Data Index: 1297851 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 3.0468. Min Range: -3.0468

Max Act: 1.5357. Min Act: -0.0000

Data Index: 412404 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 3.0468. Min Range: -3.0468

Max Act: 1.5268. Min Act: -0.0000

Data Index: 209857 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 3.0468. Min Range: -3.0468

Max Act: 1.3519. Min Act: -0.0001

Data Index: 649047 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 3.0468. Min Range: -3.0468

Max Act: 1.4350. Min Act: -0.0000

Data Index: 218694 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 3.0468. Min Range: -3.0468

Max Act: 1.4439. Min Act: -0.0000

Data Index: 1245317 (C4 (Web Text))

Max Activating Token Index: 211