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

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

Neuron 3575 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3762. Min Range: -1.3762

Max Act: 1.3762. Min Act: -0.0001

Data Index: 141972 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 1.3762. Min Range: -1.3762

Max Act: 0.8501. Min Act: -0.0001

Data Index: 287692 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 1.3762. Min Range: -1.3762

Max Act: 0.8452. Min Act: -0.0001

Data Index: 236134 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 1.3762. Min Range: -1.3762

Max Act: 0.7892. Min Act: -0.0001

Data Index: 1158340 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 1.3762. Min Range: -1.3762

Max Act: 0.7875. Min Act: -0.0001

Data Index: 214359 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 1.3762. Min Range: -1.3762

Max Act: 0.7248. Min Act: -0.0001

Data Index: 915361 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 1.3762. Min Range: -1.3762

Max Act: 0.7650. Min Act: -0.0001

Data Index: 751169 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 1.3762. Min Range: -1.3762

Max Act: 0.7371. Min Act: -0.0001

Data Index: 343103 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 1.3762. Min Range: -1.3762

Max Act: 0.7154. Min Act: -0.0001

Data Index: 668419 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 1.3762. Min Range: -1.3762

Max Act: 0.7348. Min Act: -0.0001

Data Index: 947590 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 1.3762. Min Range: -1.3762

Max Act: 0.7257. Min Act: -0.0001

Data Index: 190321 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 1.3762. Min Range: -1.3762

Max Act: 0.7144. Min Act: -0.0001

Data Index: 1200222 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 1.3762. Min Range: -1.3762

Max Act: 0.7078. Min Act: -0.0001

Data Index: 52303 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 1.3762. Min Range: -1.3762

Max Act: 0.6890. Min Act: -0.0001

Data Index: 1261639 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 1.3762. Min Range: -1.3762

Max Act: 0.6874. Min Act: -0.0001

Data Index: 976133 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 1.3762. Min Range: -1.3762

Max Act: 0.6590. Min Act: -0.0001

Data Index: 828805 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 1.3762. Min Range: -1.3762

Max Act: 0.6745. Min Act: -0.0001

Data Index: 1080630 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 1.3762. Min Range: -1.3762

Max Act: 0.6694. Min Act: -0.0001

Data Index: 286041 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 1.3762. Min Range: -1.3762

Max Act: 0.6595. Min Act: -0.0001

Data Index: 892450 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 1.3762. Min Range: -1.3762

Max Act: 0.6985. Min Act: -0.0001

Data Index: 1171588 (C4 (Web Text))

Max Activating Token Index: 784