Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2048 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2278. Min Range: -1.2278

Max Act: 1.2278. Min Act: -0.0001

Data Index: 1111803 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 1.2278. Min Range: -1.2278

Max Act: 1.1854. Min Act: -0.0000

Data Index: 235733 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 1.2278. Min Range: -1.2278

Max Act: 1.0795. Min Act: -0.0001

Data Index: 941219 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 1.2278. Min Range: -1.2278

Max Act: 1.0523. Min Act: -0.0000

Data Index: 797498 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 1.2278. Min Range: -1.2278

Max Act: 1.0195. Min Act: -0.0000

Data Index: 791024 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9295. Min Act: -0.0000

Data Index: 809409 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9535. Min Act: -0.0001

Data Index: 1255783 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9494. Min Act: -0.0000

Data Index: 346335 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9797. Min Act: -0.0000

Data Index: 116075 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9784. Min Act: -0.0001

Data Index: 888838 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9073. Min Act: -0.0001

Data Index: 163346 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9370. Min Act: -0.0001

Data Index: 1203270 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9004. Min Act: -0.0000

Data Index: 1211302 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9001. Min Act: -0.0000

Data Index: 230726 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9306. Min Act: -0.0000

Data Index: 959218 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.8924. Min Act: -0.0001

Data Index: 51786 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.9424. Min Act: -0.0000

Data Index: 982748 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.8694. Min Act: -0.0001

Data Index: 1304460 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.8855. Min Act: -0.0000

Data Index: 565724 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 1.2278. Min Range: -1.2278

Max Act: 0.8845. Min Act: -0.0000

Data Index: 501775 (C4 (Web Text))

Max Activating Token Index: 708