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

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

Neuron 4045 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2155. Min Range: -1.2155

Max Act: 1.2155. Min Act: 0.0000

Data Index: 708851 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 1.2155. Min Range: -1.2155

Max Act: 0.8792. Min Act: -0.0000

Data Index: 342128 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 1.2155. Min Range: -1.2155

Max Act: 0.8658. Min Act: 0.0000

Data Index: 829672 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 1.2155. Min Range: -1.2155

Max Act: 0.9079. Min Act: -0.0000

Data Index: 545299 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 1.2155. Min Range: -1.2155

Max Act: 0.8009. Min Act: -0.0000

Data Index: 789787 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 1.2155. Min Range: -1.2155

Max Act: 0.8179. Min Act: -0.0000

Data Index: 836492 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 1.2155. Min Range: -1.2155

Max Act: 0.8161. Min Act: 0.0000

Data Index: 1139107 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 1.2155. Min Range: -1.2155

Max Act: 0.8121. Min Act: -0.0000

Data Index: 203228 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 1.2155. Min Range: -1.2155

Max Act: 0.8147. Min Act: -0.0000

Data Index: 567269 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 1.2155. Min Range: -1.2155

Max Act: 0.7530. Min Act: -0.0000

Data Index: 1047684 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 1.2155. Min Range: -1.2155

Max Act: 0.7099. Min Act: 0.0000

Data Index: 867894 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 1.2155. Min Range: -1.2155

Max Act: 0.6935. Min Act: -0.0000

Data Index: 578302 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 1.2155. Min Range: -1.2155

Max Act: 0.7093. Min Act: -0.0000

Data Index: 731501 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 1.2155. Min Range: -1.2155

Max Act: 0.6809. Min Act: -0.0000

Data Index: 1338786 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 1.2155. Min Range: -1.2155

Max Act: 0.7000. Min Act: -0.0000

Data Index: 458326 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 1.2155. Min Range: -1.2155

Max Act: 0.6637. Min Act: -0.0000

Data Index: 949831 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 1.2155. Min Range: -1.2155

Max Act: 0.6791. Min Act: -0.0000

Data Index: 495365 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 1.2155. Min Range: -1.2155

Max Act: 0.6736. Min Act: -0.0000

Data Index: 313130 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 1.2155. Min Range: -1.2155

Max Act: 0.6640. Min Act: -0.0000

Data Index: 1294164 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 1.2155. Min Range: -1.2155

Max Act: 0.6555. Min Act: 0.0000

Data Index: 138852 (C4 (Web Text))

Max Activating Token Index: 155