Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3501 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1521. Min Act: -0.0001

Data Index: 977244 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1408. Min Act: -0.0001

Data Index: 1099784 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1397. Min Act: -0.0001

Data Index: 473426 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1323. Min Act: -0.0001

Data Index: 932375 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1240. Min Act: -0.0001

Data Index: 130570 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1193. Min Act: -0.0001

Data Index: 502566 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1201. Min Act: -0.0001

Data Index: 430552 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1161. Min Act: -0.0001

Data Index: 854326 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1104. Min Act: -0.0001

Data Index: 205366 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1105. Min Act: -0.0001

Data Index: 163111 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1085. Min Act: -0.0001

Data Index: 38205 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1120. Min Act: -0.0001

Data Index: 1057490 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1137. Min Act: -0.0001

Data Index: 996253 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1051. Min Act: -0.0001

Data Index: 70893 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1094. Min Act: -0.0001

Data Index: 1213910 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1008. Min Act: -0.0001

Data Index: 624549 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1158. Min Act: -0.0001

Data Index: 535356 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1151. Min Act: -0.0001

Data Index: 582457 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.0994. Min Act: -0.0001

Data Index: 650351 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1099. Min Act: -0.0001

Data Index: 157275 (C4 (Web Text))

Max Activating Token Index: 237