Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1713 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.4719. Min Act: -0.0000

Data Index: 15781 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.4756. Min Act: -0.0001

Data Index: 832992 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.4257. Min Act: 0.0000

Data Index: 950230 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.4222. Min Act: -0.0000

Data Index: 446596 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.4146. Min Act: -0.0000

Data Index: 1153445 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.4119. Min Act: -0.0000

Data Index: 1246152 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.4034. Min Act: -0.0001

Data Index: 1321816 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.4275. Min Act: -0.0000

Data Index: 1140352 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.4057. Min Act: -0.0000

Data Index: 1041850 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3755. Min Act: -0.0000

Data Index: 1199684 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3757. Min Act: -0.0001

Data Index: 825799 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3636. Min Act: -0.0000

Data Index: 250516 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3542. Min Act: -0.0000

Data Index: 615029 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3636. Min Act: -0.0001

Data Index: 1142973 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3706. Min Act: -0.0000

Data Index: 371800 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3569. Min Act: -0.0000

Data Index: 456805 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3548. Min Act: -0.0000

Data Index: 293009 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3570. Min Act: -0.0000

Data Index: 858865 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3630. Min Act: -0.0000

Data Index: 956427 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 0.4756. Min Range: -0.4756

Max Act: 0.3560. Min Act: -0.0001

Data Index: 198780 (C4 (Web Text))

Max Activating Token Index: 764