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

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

Neuron 429 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.4705. Min Act: -0.0003

Data Index: 39945 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.4848. Min Act: -0.0003

Data Index: 394527 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.4169. Min Act: -0.0003

Data Index: 24 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.4423. Min Act: -0.0003

Data Index: 454929 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.4664. Min Act: -0.0003

Data Index: 411177 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.4406. Min Act: -0.0003

Data Index: 1154165 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.4220. Min Act: -0.0003

Data Index: 953786 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.4510. Min Act: -0.0003

Data Index: 685250 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.4464. Min Act: -0.0003

Data Index: 551917 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.4127. Min Act: -0.0003

Data Index: 74306 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.3731. Min Act: -0.0003

Data Index: 1198796 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.4544. Min Act: -0.0003

Data Index: 1110245 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.3857. Min Act: -0.0003

Data Index: 777265 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.3938. Min Act: -0.0003

Data Index: 126913 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.4133. Min Act: -0.0003

Data Index: 743226 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.3725. Min Act: -0.0003

Data Index: 913901 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.3975. Min Act: -0.0003

Data Index: 938742 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.3263. Min Act: -0.0003

Data Index: 942777 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.3852. Min Act: -0.0003

Data Index: 1190667 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.4848. Min Range: -0.4848

Max Act: 0.3583. Min Act: -0.0003

Data Index: 1261072 (C4 (Web Text))

Max Activating Token Index: 859