Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1253 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.5641. Min Act: -0.0005

Data Index: 1043304 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.5002. Min Act: -0.0005

Data Index: 254754 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.5125. Min Act: -0.0005

Data Index: 625557 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.5080. Min Act: -0.0005

Data Index: 311576 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4951. Min Act: -0.0005

Data Index: 592455 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.5220. Min Act: -0.0005

Data Index: 1288137 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4729. Min Act: -0.0005

Data Index: 683125 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4858. Min Act: -0.0005

Data Index: 519297 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4786. Min Act: -0.0005

Data Index: 813575 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4585. Min Act: -0.0005

Data Index: 772046 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4586. Min Act: -0.0005

Data Index: 1208017 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4830. Min Act: -0.0005

Data Index: 228876 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4486. Min Act: -0.0005

Data Index: 625379 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4491. Min Act: -0.0005

Data Index: 450897 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4484. Min Act: -0.0005

Data Index: 309254 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4318. Min Act: -0.0005

Data Index: 587454 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4594. Min Act: -0.0005

Data Index: 336054 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4560. Min Act: -0.0005

Data Index: 257816 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4577. Min Act: -0.0005

Data Index: 922830 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 0.5641. Min Range: -0.5641

Max Act: 0.4551. Min Act: -0.0005

Data Index: 561676 (C4 (Web Text))

Max Activating Token Index: 588