Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1592 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1310. Min Act: -0.0002

Data Index: 869778 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1296. Min Act: -0.0002

Data Index: 381999 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1172. Min Act: -0.0002

Data Index: 287913 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1097. Min Act: -0.0002

Data Index: 617548 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0963. Min Act: -0.0002

Data Index: 37026 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0946. Min Act: -0.0002

Data Index: 628497 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0878. Min Act: -0.0002

Data Index: 1040554 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0864. Min Act: -0.0002

Data Index: 879552 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1321107 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0797. Min Act: -0.0002

Data Index: 29529 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0843. Min Act: -0.0002

Data Index: 234498 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0746. Min Act: -0.0002

Data Index: 241770 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0760. Min Act: -0.0002

Data Index: 26853 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0710. Min Act: -0.0002

Data Index: 1233543 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0721. Min Act: -0.0002

Data Index: 448322 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1125219 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0660. Min Act: -0.0002

Data Index: 369992 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0672. Min Act: -0.0002

Data Index: 578541 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0666. Min Act: -0.0002

Data Index: 1074819 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0655. Min Act: -0.0002

Data Index: 526603 (C4 (Web Text))

Max Activating Token Index: 57