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

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

Neuron 785 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3952. Min Range: -2.3952

Max Act: 2.3952. Min Act: -0.0000

Data Index: 155505 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 2.3952. Min Range: -2.3952

Max Act: 1.3962. Min Act: -0.0000

Data Index: 717204 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 2.3952. Min Range: -2.3952

Max Act: 1.3522. Min Act: -0.0000

Data Index: 1250239 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 2.3952. Min Range: -2.3952

Max Act: 1.2160. Min Act: -0.0000

Data Index: 186715 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 2.3952. Min Range: -2.3952

Max Act: 1.0614. Min Act: -0.0000

Data Index: 254924 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 2.3952. Min Range: -2.3952

Max Act: 1.1106. Min Act: -0.0000

Data Index: 776250 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 2.3952. Min Range: -2.3952

Max Act: 0.9850. Min Act: -0.0000

Data Index: 642028 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 2.3952. Min Range: -2.3952

Max Act: 0.9809. Min Act: -0.0000

Data Index: 652756 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 2.3952. Min Range: -2.3952

Max Act: 0.9800. Min Act: -0.0000

Data Index: 1241113 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 2.3952. Min Range: -2.3952

Max Act: 0.9565. Min Act: -0.0000

Data Index: 545428 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 2.3952. Min Range: -2.3952

Max Act: 1.0153. Min Act: -0.0000

Data Index: 613681 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 2.3952. Min Range: -2.3952

Max Act: 0.9391. Min Act: -0.0000

Data Index: 910250 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 2.3952. Min Range: -2.3952

Max Act: 0.9097. Min Act: -0.0000

Data Index: 416596 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 2.3952. Min Range: -2.3952

Max Act: 0.9298. Min Act: -0.0000

Data Index: 744741 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 2.3952. Min Range: -2.3952

Max Act: 0.8917. Min Act: -0.0000

Data Index: 998562 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 2.3952. Min Range: -2.3952

Max Act: 0.7464. Min Act: -0.0000

Data Index: 1269466 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 2.3952. Min Range: -2.3952

Max Act: 0.7679. Min Act: -0.0000

Data Index: 445397 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 2.3952. Min Range: -2.3952

Max Act: 0.8174. Min Act: -0.0000

Data Index: 1230590 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 2.3952. Min Range: -2.3952

Max Act: 0.7951. Min Act: -0.0000

Data Index: 561062 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 2.3952. Min Range: -2.3952

Max Act: 0.8112. Min Act: -0.0000

Data Index: 278792 (C4 (Web Text))

Max Activating Token Index: 838