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

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

Neuron 3070 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: 2.6273. Min Range: -2.6273

Max Act: 2.6273. Min Act: -0.0000

Data Index: 166020 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 2.6273. Min Range: -2.6273

Max Act: 2.1646. Min Act: -0.0000

Data Index: 1315992 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 2.6273. Min Range: -2.6273

Max Act: 1.9797. Min Act: 0.0000

Data Index: 746994 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 2.6273. Min Range: -2.6273

Max Act: 2.0326. Min Act: -0.0000

Data Index: 560299 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 2.6273. Min Range: -2.6273

Max Act: 1.9645. Min Act: -0.0000

Data Index: 1063679 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 2.6273. Min Range: -2.6273

Max Act: 2.0669. Min Act: -0.0000

Data Index: 42359 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 2.6273. Min Range: -2.6273

Max Act: 1.9420. Min Act: -0.0000

Data Index: 1096190 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 2.6273. Min Range: -2.6273

Max Act: 1.7817. Min Act: -0.0000

Data Index: 1137536 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 2.6273. Min Range: -2.6273

Max Act: 1.9748. Min Act: -0.0000

Data Index: 1113076 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 2.6273. Min Range: -2.6273

Max Act: 1.8650. Min Act: -0.0000

Data Index: 1068224 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 2.6273. Min Range: -2.6273

Max Act: 1.8397. Min Act: -0.0000

Data Index: 519720 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 2.6273. Min Range: -2.6273

Max Act: 1.8157. Min Act: 0.0001

Data Index: 720877 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 2.6273. Min Range: -2.6273

Max Act: 1.8231. Min Act: -0.0000

Data Index: 1061322 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 2.6273. Min Range: -2.6273

Max Act: 1.7020. Min Act: -0.0000

Data Index: 1152964 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 2.6273. Min Range: -2.6273

Max Act: 1.8086. Min Act: 0.0001

Data Index: 124701 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 2.6273. Min Range: -2.6273

Max Act: 1.7930. Min Act: -0.0000

Data Index: 1257557 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 2.6273. Min Range: -2.6273

Max Act: 1.7778. Min Act: -0.0000

Data Index: 1228000 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 2.6273. Min Range: -2.6273

Max Act: 1.7788. Min Act: -0.0000

Data Index: 559028 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 2.6273. Min Range: -2.6273

Max Act: 1.6835. Min Act: 0.0000

Data Index: 693675 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 2.6273. Min Range: -2.6273

Max Act: 1.7613. Min Act: -0.0000

Data Index: 243601 (C4 (Web Text))

Max Activating Token Index: 895