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

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

Neuron 5539 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.9254. Min Act: -0.0001

Data Index: 431764 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.8526. Min Act: -0.0001

Data Index: 476495 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.8922. Min Act: -0.0001

Data Index: 871760 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.7305. Min Act: -0.0001

Data Index: 991671 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.7471. Min Act: -0.0001

Data Index: 240006 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.7572. Min Act: -0.0001

Data Index: 6205 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.7213. Min Act: -0.0001

Data Index: 1047733 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.6705. Min Act: -0.0001

Data Index: 706484 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.6787. Min Act: -0.0001

Data Index: 716916 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.7852. Min Act: -0.0001

Data Index: 606697 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.6627. Min Act: -0.0001

Data Index: 835520 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.7090. Min Act: -0.0001

Data Index: 142087 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.7100. Min Act: -0.0001

Data Index: 1342273 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.6512. Min Act: -0.0001

Data Index: 663981 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.6387. Min Act: -0.0001

Data Index: 1347855 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.6438. Min Act: -0.0001

Data Index: 1257745 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.7380. Min Act: -0.0001

Data Index: 877431 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.6881. Min Act: -0.0001

Data Index: 1305938 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.6624. Min Act: -0.0001

Data Index: 412799 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.6273. Min Act: -0.0001

Data Index: 1118628 (C4 (Web Text))

Max Activating Token Index: 244