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

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

Neuron 4811 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1107. Min Range: -1.1107

Max Act: 1.1107. Min Act: -0.0000

Data Index: 855917 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 1.1107. Min Range: -1.1107

Max Act: 1.0943. Min Act: -0.0000

Data Index: 462887 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 1.1107. Min Range: -1.1107

Max Act: 1.0948. Min Act: -0.0000

Data Index: 1161473 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 1.1107. Min Range: -1.1107

Max Act: 1.0456. Min Act: -0.0000

Data Index: 779820 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 1.1107. Min Range: -1.1107

Max Act: 1.0019. Min Act: -0.0000

Data Index: 518304 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 1.1107. Min Range: -1.1107

Max Act: 1.0375. Min Act: -0.0000

Data Index: 628099 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8825. Min Act: -0.0000

Data Index: 187451 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.9160. Min Act: -0.0000

Data Index: 208133 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8736. Min Act: -0.0000

Data Index: 209085 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8802. Min Act: -0.0000

Data Index: 606466 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8678. Min Act: -0.0000

Data Index: 975799 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8595. Min Act: -0.0000

Data Index: 947599 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8349. Min Act: -0.0000

Data Index: 497351 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8856. Min Act: -0.0000

Data Index: 574754 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8626. Min Act: -0.0000

Data Index: 1002814 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8641. Min Act: -0.0000

Data Index: 182004 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.9085. Min Act: -0.0000

Data Index: 503921 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8460. Min Act: -0.0000

Data Index: 1102565 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8500. Min Act: -0.0000

Data Index: 172154 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8478. Min Act: -0.0000

Data Index: 922584 (C4 (Web Text))

Max Activating Token Index: 52