Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3950 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.6651. Min Act: -0.0000

Data Index: 56163 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.6487. Min Act: -0.0000

Data Index: 409776 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1041385 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1605280 (Python Code)

Max Activating Token Index: 701

Text #4

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1329636 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.6226. Min Act: -0.0000

Data Index: 1139120 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.5694. Min Act: -0.0000

Data Index: 1341765 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.5441. Min Act: -0.0000

Data Index: 1100024 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.5136. Min Act: -0.0000

Data Index: 156975 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4956. Min Act: -0.0000

Data Index: 143815 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1335927 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4953. Min Act: -0.0000

Data Index: 884342 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4975. Min Act: -0.0000

Data Index: 878129 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4986. Min Act: -0.0000

Data Index: 902033 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.5070. Min Act: 0.0000

Data Index: 1339302 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4768. Min Act: -0.0000

Data Index: 401779 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4772. Min Act: -0.0000

Data Index: 318718 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4814. Min Act: -0.0000

Data Index: 580543 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4813. Min Act: -0.0000

Data Index: 820384 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 0.6651. Min Range: -0.6651

Max Act: 0.4809. Min Act: -0.0000

Data Index: 963238 (C4 (Web Text))

Max Activating Token Index: 109