Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5144 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 9.2194. Min Range: -9.2194

Max Act: 9.1714. Min Act: -0.0000

Data Index: 755125 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 9.2194. Min Range: -9.2194

Max Act: 8.8023. Min Act: -0.0000

Data Index: 193898 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 9.2194. Min Range: -9.2194

Max Act: 9.2194. Min Act: -0.0000

Data Index: 93232 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 9.2194. Min Range: -9.2194

Max Act: 8.2899. Min Act: -0.0000

Data Index: 553815 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 9.2194. Min Range: -9.2194

Max Act: 8.4270. Min Act: -0.0000

Data Index: 653280 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 9.2194. Min Range: -9.2194

Max Act: 8.0522. Min Act: -0.0000

Data Index: 52558 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 9.2194. Min Range: -9.2194

Max Act: 7.3823. Min Act: -0.0000

Data Index: 167130 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 9.2194. Min Range: -9.2194

Max Act: 7.9119. Min Act: -0.0000

Data Index: 19897 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 9.2194. Min Range: -9.2194

Max Act: 7.8408. Min Act: -0.0000

Data Index: 854480 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 9.2194. Min Range: -9.2194

Max Act: 7.4698. Min Act: -0.0000

Data Index: 629376 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 9.2194. Min Range: -9.2194

Max Act: 8.1715. Min Act: -0.0000

Data Index: 1271941 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 9.2194. Min Range: -9.2194

Max Act: 7.9620. Min Act: -0.0000

Data Index: 574731 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 9.2194. Min Range: -9.2194

Max Act: 7.5790. Min Act: -0.0000

Data Index: 575521 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 9.2194. Min Range: -9.2194

Max Act: 8.1316. Min Act: -0.0000

Data Index: 832318 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 9.2194. Min Range: -9.2194

Max Act: 7.5104. Min Act: -0.0000

Data Index: 627584 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 9.2194. Min Range: -9.2194

Max Act: 7.9065. Min Act: -0.0000

Data Index: 21540 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 9.2194. Min Range: -9.2194

Max Act: 7.8387. Min Act: -0.0000

Data Index: 881336 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 9.2194. Min Range: -9.2194

Max Act: 7.4023. Min Act: -0.0000

Data Index: 527888 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 9.2194. Min Range: -9.2194

Max Act: 7.4073. Min Act: -0.0000

Data Index: 590981 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 9.2194. Min Range: -9.2194

Max Act: 7.7203. Min Act: -0.0000

Data Index: 49495 (C4 (Web Text))

Max Activating Token Index: 513