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

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

Neuron 4702 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6162. Min Range: -1.6162

Max Act: 1.6162. Min Act: -0.0000

Data Index: 201584 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 1.6162. Min Range: -1.6162

Max Act: 1.0800. Min Act: -0.0000

Data Index: 70606 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 1.6162. Min Range: -1.6162

Max Act: 0.6993. Min Act: -0.0000

Data Index: 38312 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 1.6162. Min Range: -1.6162

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1140630 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 1.6162. Min Range: -1.6162

Max Act: 0.7843. Min Act: -0.0000

Data Index: 572807 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 1.6162. Min Range: -1.6162

Max Act: 0.6669. Min Act: -0.0000

Data Index: 366090 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 1.6162. Min Range: -1.6162

Max Act: 0.7549. Min Act: -0.0000

Data Index: 392090 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 1.6162. Min Range: -1.6162

Max Act: 0.7434. Min Act: -0.0000

Data Index: 762905 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 1.6162. Min Range: -1.6162

Max Act: 0.6754. Min Act: -0.0000

Data Index: 154581 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 1.6162. Min Range: -1.6162

Max Act: 0.6728. Min Act: -0.0000

Data Index: 432566 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 1.6162. Min Range: -1.6162

Max Act: 0.6595. Min Act: -0.0000

Data Index: 675039 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 1.6162. Min Range: -1.6162

Max Act: 0.6334. Min Act: -0.0000

Data Index: 550843 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 1.6162. Min Range: -1.6162

Max Act: 0.6531. Min Act: -0.0000

Data Index: 1248781 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 1.6162. Min Range: -1.6162

Max Act: 0.5955. Min Act: -0.0000

Data Index: 545108 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 1.6162. Min Range: -1.6162

Max Act: 0.6249. Min Act: -0.0000

Data Index: 72297 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 1.6162. Min Range: -1.6162

Max Act: 0.6182. Min Act: -0.0000

Data Index: 69722 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 1.6162. Min Range: -1.6162

Max Act: 0.6839. Min Act: -0.0000

Data Index: 1245741 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 1.6162. Min Range: -1.6162

Max Act: 0.5923. Min Act: -0.0000

Data Index: 1035028 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 1.6162. Min Range: -1.6162

Max Act: 0.6104. Min Act: -0.0000

Data Index: 634634 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 1.6162. Min Range: -1.6162

Max Act: 0.6161. Min Act: -0.0000

Data Index: 209226 (C4 (Web Text))

Max Activating Token Index: 113