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

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

Neuron 3124 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: 5.3058. Min Range: -5.3058

Max Act: 5.3058. Min Act: -0.0001

Data Index: 980763 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 5.3058. Min Range: -5.3058

Max Act: 5.2340. Min Act: -0.0001

Data Index: 808295 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 5.3058. Min Range: -5.3058

Max Act: 3.7989. Min Act: -0.0001

Data Index: 391260 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 5.3058. Min Range: -5.3058

Max Act: 4.1192. Min Act: -0.0001

Data Index: 36885 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 5.3058. Min Range: -5.3058

Max Act: 3.7620. Min Act: -0.0001

Data Index: 1293526 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 5.3058. Min Range: -5.3058

Max Act: 4.0595. Min Act: -0.0001

Data Index: 435790 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 5.3058. Min Range: -5.3058

Max Act: 4.3891. Min Act: -0.0001

Data Index: 567860 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 5.3058. Min Range: -5.3058

Max Act: 4.0285. Min Act: -0.0001

Data Index: 642765 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 5.3058. Min Range: -5.3058

Max Act: 4.1111. Min Act: -0.0001

Data Index: 63444 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 5.3058. Min Range: -5.3058

Max Act: 4.1169. Min Act: -0.0001

Data Index: 1125079 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 5.3058. Min Range: -5.3058

Max Act: 3.5904. Min Act: -0.0001

Data Index: 886074 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 5.3058. Min Range: -5.3058

Max Act: 3.9977. Min Act: -0.0001

Data Index: 705922 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 5.3058. Min Range: -5.3058

Max Act: 3.4546. Min Act: -0.0001

Data Index: 191909 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 5.3058. Min Range: -5.3058

Max Act: 3.5656. Min Act: -0.0001

Data Index: 1172457 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 5.3058. Min Range: -5.3058

Max Act: 3.6478. Min Act: -0.0001

Data Index: 1352219 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 5.3058. Min Range: -5.3058

Max Act: 3.7229. Min Act: -0.0001

Data Index: 844271 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 5.3058. Min Range: -5.3058

Max Act: 3.3718. Min Act: -0.0001

Data Index: 873654 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 5.3058. Min Range: -5.3058

Max Act: 3.4063. Min Act: -0.0001

Data Index: 156655 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 5.3058. Min Range: -5.3058

Max Act: 3.3184. Min Act: -0.0001

Data Index: 323272 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 5.3058. Min Range: -5.3058

Max Act: 2.7741. Min Act: -0.0001

Data Index: 167965 (C4 (Web Text))

Max Activating Token Index: 178