Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 932 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1330. Min Act: -0.0001

Data Index: 364690 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1161558 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1157. Min Act: -0.0001

Data Index: 687933 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1190315 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1168. Min Act: -0.0001

Data Index: 833791 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1157. Min Act: -0.0001

Data Index: 346265 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1030550 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1048. Min Act: -0.0001

Data Index: 449055 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.1000. Min Act: -0.0001

Data Index: 259464 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0925. Min Act: -0.0001

Data Index: 1303348 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0988. Min Act: -0.0001

Data Index: 986870 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0955. Min Act: -0.0001

Data Index: 264735 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0950. Min Act: -0.0001

Data Index: 306101 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0953. Min Act: -0.0001

Data Index: 335478 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0937. Min Act: -0.0001

Data Index: 967320 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0913. Min Act: -0.0001

Data Index: 205726 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0892. Min Act: -0.0001

Data Index: 116789 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0898. Min Act: -0.0001

Data Index: 1254443 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1125732 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 0.1330. Min Range: -0.1330

Max Act: 0.0935. Min Act: -0.0001

Data Index: 171199 (C4 (Web Text))

Max Activating Token Index: 1017