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

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

Neuron 2021 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: 0.5824. Min Range: -0.5824

Max Act: 0.5645. Min Act: -0.0000

Data Index: 258111 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.5824. Min Act: -0.0000

Data Index: 131314 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.5205. Min Act: -0.0000

Data Index: 1070849 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.5192. Min Act: -0.0000

Data Index: 784730 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.5051. Min Act: -0.0000

Data Index: 872208 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4854. Min Act: -0.0000

Data Index: 697297 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4987. Min Act: -0.0000

Data Index: 301029 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4987. Min Act: -0.0000

Data Index: 690462 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.5166. Min Act: -0.0000

Data Index: 199699 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4861. Min Act: -0.0000

Data Index: 1194875 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4983. Min Act: -0.0000

Data Index: 1339999 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4758. Min Act: -0.0000

Data Index: 415737 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4670. Min Act: -0.0000

Data Index: 416552 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4667. Min Act: -0.0000

Data Index: 94328 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1287821 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4466. Min Act: 0.0001

Data Index: 1131489 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4598. Min Act: -0.0000

Data Index: 445595 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4507. Min Act: -0.0000

Data Index: 298082 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4684. Min Act: -0.0000

Data Index: 242654 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4519. Min Act: -0.0000

Data Index: 537015 (C4 (Web Text))

Max Activating Token Index: 563