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

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

Neuron 5044 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3246. Min Range: -7.3246

Max Act: 7.3246. Min Act: -0.0001

Data Index: 4865 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 7.3246. Min Range: -7.3246

Max Act: 6.7759. Min Act: -0.0000

Data Index: 1045390 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 7.3246. Min Range: -7.3246

Max Act: 6.3462. Min Act: -0.0000

Data Index: 683017 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 7.3246. Min Range: -7.3246

Max Act: 6.1553. Min Act: -0.0000

Data Index: 198585 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 7.3246. Min Range: -7.3246

Max Act: 5.6541. Min Act: -0.0000

Data Index: 151357 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 7.3246. Min Range: -7.3246

Max Act: 5.5733. Min Act: -0.0001

Data Index: 688262 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 7.3246. Min Range: -7.3246

Max Act: 5.5085. Min Act: -0.0000

Data Index: 285602 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 7.3246. Min Range: -7.3246

Max Act: 5.5770. Min Act: -0.0001

Data Index: 34536 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 7.3246. Min Range: -7.3246

Max Act: 5.4697. Min Act: -0.0001

Data Index: 141777 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 7.3246. Min Range: -7.3246

Max Act: 5.4599. Min Act: -0.0001

Data Index: 898839 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 7.3246. Min Range: -7.3246

Max Act: 5.2522. Min Act: -0.0001

Data Index: 193159 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 7.3246. Min Range: -7.3246

Max Act: 5.4861. Min Act: -0.0000

Data Index: 756537 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 7.3246. Min Range: -7.3246

Max Act: 5.1160. Min Act: -0.0001

Data Index: 85454 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 7.3246. Min Range: -7.3246

Max Act: 4.9293. Min Act: -0.0001

Data Index: 922854 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 7.3246. Min Range: -7.3246

Max Act: 5.1968. Min Act: -0.0000

Data Index: 1148247 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 7.3246. Min Range: -7.3246

Max Act: 5.0210. Min Act: -0.0001

Data Index: 965158 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 7.3246. Min Range: -7.3246

Max Act: 5.3248. Min Act: -0.0001

Data Index: 1073264 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 7.3246. Min Range: -7.3246

Max Act: 5.0895. Min Act: -0.0001

Data Index: 896869 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 7.3246. Min Range: -7.3246

Max Act: 5.0562. Min Act: -0.0001

Data Index: 1330336 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 7.3246. Min Range: -7.3246

Max Act: 4.7171. Min Act: -0.0000

Data Index: 200207 (C4 (Web Text))

Max Activating Token Index: 194