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

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

Neuron 1876 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.5874. Min Act: -0.0002

Data Index: 668135 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.5168. Min Act: -0.0002

Data Index: 810377 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4628. Min Act: -0.0002

Data Index: 1251005 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4713. Min Act: -0.0002

Data Index: 1003067 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4333. Min Act: -0.0003

Data Index: 205174 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4110. Min Act: -0.0002

Data Index: 1353495 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4199. Min Act: -0.0003

Data Index: 1264809 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4287. Min Act: -0.0003

Data Index: 666023 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4130. Min Act: -0.0003

Data Index: 890577 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4108. Min Act: -0.0003

Data Index: 1181123 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4088. Min Act: -0.0002

Data Index: 900807 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4041. Min Act: -0.0003

Data Index: 404615 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4011. Min Act: -0.0003

Data Index: 792230 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.3848. Min Act: -0.0003

Data Index: 148487 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.3823. Min Act: -0.0002

Data Index: 353396 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.3879. Min Act: -0.0002

Data Index: 306468 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.3851. Min Act: -0.0003

Data Index: 111222 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.3705. Min Act: -0.0003

Data Index: 853524 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.3825. Min Act: -0.0002

Data Index: 102640 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.3814. Min Act: -0.0003

Data Index: 1048464 (C4 (Web Text))

Max Activating Token Index: 48