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

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

Neuron 2468 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0654. Min Range: -3.0654

Max Act: 3.0654. Min Act: -0.0000

Data Index: 810411 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 3.0654. Min Range: -3.0654

Max Act: 2.5359. Min Act: -0.0000

Data Index: 896007 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 3.0654. Min Range: -3.0654

Max Act: 2.3831. Min Act: -0.0000

Data Index: 181500 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 3.0654. Min Range: -3.0654

Max Act: 2.4642. Min Act: -0.0000

Data Index: 1632586 (Python Code)

Max Activating Token Index: 769

Text #4

Max Range: 3.0654. Min Range: -3.0654

Max Act: 2.0753. Min Act: -0.0000

Data Index: 1003819 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 3.0654. Min Range: -3.0654

Max Act: 2.2827. Min Act: -0.0000

Data Index: 177207 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 3.0654. Min Range: -3.0654

Max Act: 2.1984. Min Act: -0.0000

Data Index: 183942 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 3.0654. Min Range: -3.0654

Max Act: 2.1651. Min Act: -0.0000

Data Index: 169436 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 3.0654. Min Range: -3.0654

Max Act: 2.0517. Min Act: -0.0000

Data Index: 889068 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 3.0654. Min Range: -3.0654

Max Act: 2.2364. Min Act: -0.0001

Data Index: 593287 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 3.0654. Min Range: -3.0654

Max Act: 2.0163. Min Act: -0.0001

Data Index: 31259 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 3.0654. Min Range: -3.0654

Max Act: 2.1336. Min Act: -0.0000

Data Index: 1054736 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 3.0654. Min Range: -3.0654

Max Act: 2.0933. Min Act: -0.0000

Data Index: 48017 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 3.0654. Min Range: -3.0654

Max Act: 1.8717. Min Act: -0.0001

Data Index: 350628 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 3.0654. Min Range: -3.0654

Max Act: 2.0307. Min Act: -0.0000

Data Index: 1155689 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 3.0654. Min Range: -3.0654

Max Act: 1.9088. Min Act: -0.0001

Data Index: 1202143 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 3.0654. Min Range: -3.0654

Max Act: 2.0023. Min Act: -0.0000

Data Index: 321105 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 3.0654. Min Range: -3.0654

Max Act: 1.9771. Min Act: -0.0000

Data Index: 428646 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 3.0654. Min Range: -3.0654

Max Act: 1.8821. Min Act: -0.0000

Data Index: 1059143 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 3.0654. Min Range: -3.0654

Max Act: 1.9957. Min Act: -0.0000

Data Index: 296382 (C4 (Web Text))

Max Activating Token Index: 98