Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3158 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.1025. Min Act: -0.0001

Data Index: 1327668 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.1692. Min Act: -0.0001

Data Index: 773902 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.0058. Min Act: -0.0001

Data Index: 895612 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.9886. Min Act: -0.0001

Data Index: 190706 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.9021. Min Act: -0.0001

Data Index: 581313 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.8012. Min Act: -0.0001

Data Index: 1161331 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.8551. Min Act: -0.0001

Data Index: 515444 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.8342. Min Act: -0.0001

Data Index: 914323 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 1.1692. Min Range: -1.1692

Max Act: 1.0875. Min Act: -0.0001

Data Index: 332716 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.9239. Min Act: -0.0001

Data Index: 652087 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.7959. Min Act: -0.0001

Data Index: 962749 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.8474. Min Act: -0.0001

Data Index: 124048 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.7782. Min Act: -0.0001

Data Index: 616314 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.8232. Min Act: -0.0001

Data Index: 200803 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.8412. Min Act: -0.0001

Data Index: 447551 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.8365. Min Act: -0.0001

Data Index: 527242 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.7890. Min Act: -0.0001

Data Index: 1327286 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.7960. Min Act: -0.0001

Data Index: 261465 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.7324. Min Act: -0.0001

Data Index: 1256223 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 1.1692. Min Range: -1.1692

Max Act: 0.7413. Min Act: -0.0001

Data Index: 309492 (C4 (Web Text))

Max Activating Token Index: 724