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

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

Neuron 203 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1210. Min Range: -3.1210

Max Act: 3.1210. Min Act: -0.0000

Data Index: 295586 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.6406. Min Act: -0.0000

Data Index: 795498 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.6886. Min Act: -0.0000

Data Index: 714123 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.5614. Min Act: -0.0000

Data Index: 341755 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.2791. Min Act: -0.0000

Data Index: 1268787 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.3694. Min Act: -0.0000

Data Index: 879940 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.0870. Min Act: -0.0000

Data Index: 732126 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.0642. Min Act: -0.0000

Data Index: 463574 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.1176. Min Act: -0.0000

Data Index: 289118 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 3.1210. Min Range: -3.1210

Max Act: 1.9431. Min Act: -0.0000

Data Index: 317436 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.1316. Min Act: -0.0000

Data Index: 780265 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 3.1210. Min Range: -3.1210

Max Act: 1.9167. Min Act: -0.0000

Data Index: 47455 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 3.1210. Min Range: -3.1210

Max Act: 1.6700. Min Act: -0.0000

Data Index: 823855 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 3.1210. Min Range: -3.1210

Max Act: 1.9303. Min Act: -0.0000

Data Index: 244714 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 3.1210. Min Range: -3.1210

Max Act: 1.9437. Min Act: -0.0000

Data Index: 683724 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 3.1210. Min Range: -3.1210

Max Act: 1.8438. Min Act: -0.0000

Data Index: 100532 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 3.1210. Min Range: -3.1210

Max Act: 1.9118. Min Act: -0.0000

Data Index: 255216 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 3.1210. Min Range: -3.1210

Max Act: 1.8644. Min Act: -0.0000

Data Index: 834058 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 3.1210. Min Range: -3.1210

Max Act: 1.8671. Min Act: -0.0000

Data Index: 984273 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 3.1210. Min Range: -3.1210

Max Act: 1.8407. Min Act: -0.0000

Data Index: 1153240 (C4 (Web Text))

Max Activating Token Index: 717