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

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

Neuron 2750 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9215. Min Range: -2.9215

Max Act: 2.9215. Min Act: -0.0000

Data Index: 166440 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 2.9215. Min Range: -2.9215

Max Act: 2.5711. Min Act: -0.0000

Data Index: 653286 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 2.9215. Min Range: -2.9215

Max Act: 2.4900. Min Act: -0.0000

Data Index: 480213 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 2.9215. Min Range: -2.9215

Max Act: 2.6325. Min Act: -0.0000

Data Index: 823374 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 2.9215. Min Range: -2.9215

Max Act: 2.4429. Min Act: -0.0000

Data Index: 488988 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 2.9215. Min Range: -2.9215

Max Act: 2.3836. Min Act: -0.0000

Data Index: 77698 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 2.9215. Min Range: -2.9215

Max Act: 2.3981. Min Act: -0.0000

Data Index: 628567 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 2.9215. Min Range: -2.9215

Max Act: 2.2268. Min Act: -0.0000

Data Index: 614953 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 2.9215. Min Range: -2.9215

Max Act: 2.1201. Min Act: -0.0000

Data Index: 132998 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 2.9215. Min Range: -2.9215

Max Act: 2.0677. Min Act: -0.0000

Data Index: 150526 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 2.9215. Min Range: -2.9215

Max Act: 1.9693. Min Act: -0.0000

Data Index: 260182 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 2.9215. Min Range: -2.9215

Max Act: 2.0714. Min Act: -0.0000

Data Index: 260037 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 2.9215. Min Range: -2.9215

Max Act: 2.0032. Min Act: -0.0000

Data Index: 1302990 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 2.9215. Min Range: -2.9215

Max Act: 1.9982. Min Act: -0.0000

Data Index: 441827 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 2.9215. Min Range: -2.9215

Max Act: 1.9818. Min Act: -0.0000

Data Index: 842163 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 2.9215. Min Range: -2.9215

Max Act: 1.8681. Min Act: -0.0000

Data Index: 195309 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 2.9215. Min Range: -2.9215

Max Act: 1.9649. Min Act: -0.0000

Data Index: 701950 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 2.9215. Min Range: -2.9215

Max Act: 1.8455. Min Act: -0.0000

Data Index: 913899 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 2.9215. Min Range: -2.9215

Max Act: 1.9523. Min Act: -0.0000

Data Index: 1181436 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 2.9215. Min Range: -2.9215

Max Act: 1.8199. Min Act: -0.0000

Data Index: 1210881 (C4 (Web Text))

Max Activating Token Index: 777