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

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

Neuron 2681 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.5677. Min Act: -0.0004

Data Index: 556335 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.5299. Min Act: -0.0004

Data Index: 383491 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.3103. Min Act: -0.0004

Data Index: 831202 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.2890. Min Act: -0.0004

Data Index: 1083081 (C4 (Web Text))

Max Activating Token Index: 919

Text #4

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.1497. Min Act: -0.0004

Data Index: 924600 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.0905. Min Act: -0.0004

Data Index: 25650 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 3.5677. Min Range: -3.5677

Max Act: 2.3430. Min Act: -0.0004

Data Index: 434674 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 3.5677. Min Range: -3.5677

Max Act: 2.5291. Min Act: -0.0004

Data Index: 558050 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 3.5677. Min Range: -3.5677

Max Act: 2.5754. Min Act: -0.0004

Data Index: 751445 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 3.5677. Min Range: -3.5677

Max Act: 2.1366. Min Act: -0.0004

Data Index: 149429 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 3.5677. Min Range: -3.5677

Max Act: 2.2734. Min Act: -0.0004

Data Index: 498693 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 3.5677. Min Range: -3.5677

Max Act: 2.2674. Min Act: -0.0004

Data Index: 868918 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 3.5677. Min Range: -3.5677

Max Act: 1.7329. Min Act: -0.0004

Data Index: 409936 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 3.5677. Min Range: -3.5677

Max Act: 2.5507. Min Act: -0.0004

Data Index: 45179 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 3.5677. Min Range: -3.5677

Max Act: 1.9733. Min Act: -0.0004

Data Index: 985971 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 3.5677. Min Range: -3.5677

Max Act: 2.2190. Min Act: -0.0004

Data Index: 430347 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 3.5677. Min Range: -3.5677

Max Act: 1.9027. Min Act: -0.0004

Data Index: 1324312 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 3.5677. Min Range: -3.5677

Max Act: 2.0001. Min Act: -0.0004

Data Index: 1028080 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 3.5677. Min Range: -3.5677

Max Act: 1.9924. Min Act: -0.0004

Data Index: 514512 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 3.5677. Min Range: -3.5677

Max Act: 1.8780. Min Act: -0.0004

Data Index: 1291742 (C4 (Web Text))

Max Activating Token Index: 61