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

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

Neuron 5143 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.1384. Min Range: -2.1384

Max Act: 2.1384. Min Act: -0.0002

Data Index: 289684 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 2.1384. Min Range: -2.1384

Max Act: 2.0979. Min Act: -0.0002

Data Index: 1108142 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 2.1384. Min Range: -2.1384

Max Act: 2.0385. Min Act: -0.0002

Data Index: 359036 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 2.1384. Min Range: -2.1384

Max Act: 1.9038. Min Act: -0.0002

Data Index: 162257 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 2.1384. Min Range: -2.1384

Max Act: 1.8833. Min Act: -0.0002

Data Index: 840056 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 2.1384. Min Range: -2.1384

Max Act: 1.8043. Min Act: -0.0002

Data Index: 1155418 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 2.1384. Min Range: -2.1384

Max Act: 1.8055. Min Act: -0.0002

Data Index: 1139595 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 2.1384. Min Range: -2.1384

Max Act: 1.8270. Min Act: -0.0002

Data Index: 514014 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 2.1384. Min Range: -2.1384

Max Act: 1.7979. Min Act: -0.0002

Data Index: 1344613 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 2.1384. Min Range: -2.1384

Max Act: 1.7430. Min Act: -0.0002

Data Index: 1098972 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 2.1384. Min Range: -2.1384

Max Act: 1.8054. Min Act: -0.0002

Data Index: 1249879 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 2.1384. Min Range: -2.1384

Max Act: 1.8080. Min Act: -0.0002

Data Index: 272452 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 2.1384. Min Range: -2.1384

Max Act: 1.7819. Min Act: -0.0002

Data Index: 912988 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 2.1384. Min Range: -2.1384

Max Act: 1.7585. Min Act: -0.0002

Data Index: 1106806 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 2.1384. Min Range: -2.1384

Max Act: 1.7497. Min Act: -0.0002

Data Index: 1110114 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 2.1384. Min Range: -2.1384

Max Act: 1.7812. Min Act: -0.0002

Data Index: 136562 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 2.1384. Min Range: -2.1384

Max Act: 1.7841. Min Act: -0.0002

Data Index: 978069 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 2.1384. Min Range: -2.1384

Max Act: 1.7964. Min Act: -0.0002

Data Index: 924524 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 2.1384. Min Range: -2.1384

Max Act: 1.6915. Min Act: -0.0002

Data Index: 910667 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 2.1384. Min Range: -2.1384

Max Act: 1.7390. Min Act: -0.0002

Data Index: 460236 (C4 (Web Text))

Max Activating Token Index: 3