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

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

Neuron 1594 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: 5.0106. Min Range: -5.0106

Max Act: 5.0106. Min Act: -0.0001

Data Index: 662007 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 5.0106. Min Range: -5.0106

Max Act: 4.2409. Min Act: -0.0001

Data Index: 556875 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 5.0106. Min Range: -5.0106

Max Act: 4.5642. Min Act: -0.0001

Data Index: 1232933 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 5.0106. Min Range: -5.0106

Max Act: 4.2183. Min Act: -0.0001

Data Index: 1053775 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 5.0106. Min Range: -5.0106

Max Act: 3.7854. Min Act: -0.0001

Data Index: 419048 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 5.0106. Min Range: -5.0106

Max Act: 4.2864. Min Act: -0.0001

Data Index: 1321075 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 5.0106. Min Range: -5.0106

Max Act: 3.8690. Min Act: -0.0001

Data Index: 944520 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 5.0106. Min Range: -5.0106

Max Act: 3.6963. Min Act: -0.0001

Data Index: 777876 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 5.0106. Min Range: -5.0106

Max Act: 3.7866. Min Act: -0.0001

Data Index: 941784 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 5.0106. Min Range: -5.0106

Max Act: 3.4748. Min Act: -0.0001

Data Index: 898595 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 5.0106. Min Range: -5.0106

Max Act: 3.6294. Min Act: -0.0001

Data Index: 116171 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 5.0106. Min Range: -5.0106

Max Act: 3.8994. Min Act: -0.0001

Data Index: 206206 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 5.0106. Min Range: -5.0106

Max Act: 3.8711. Min Act: -0.0001

Data Index: 283436 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 5.0106. Min Range: -5.0106

Max Act: 3.8314. Min Act: -0.0001

Data Index: 1065106 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 5.0106. Min Range: -5.0106

Max Act: 3.7340. Min Act: -0.0001

Data Index: 1171909 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 5.0106. Min Range: -5.0106

Max Act: 3.8983. Min Act: -0.0001

Data Index: 380370 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 5.0106. Min Range: -5.0106

Max Act: 3.9012. Min Act: -0.0001

Data Index: 421729 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 5.0106. Min Range: -5.0106

Max Act: 3.3846. Min Act: -0.0001

Data Index: 747231 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 5.0106. Min Range: -5.0106

Max Act: 3.7267. Min Act: -0.0001

Data Index: 684092 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 5.0106. Min Range: -5.0106

Max Act: 3.6590. Min Act: -0.0001

Data Index: 705952 (C4 (Web Text))

Max Activating Token Index: 868