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

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

Neuron 2015 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.9070. Min Act: -0.0000

Data Index: 952965 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.8919. Min Act: -0.0000

Data Index: 48013 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.8659. Min Act: -0.0000

Data Index: 1062286 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.8185. Min Act: -0.0000

Data Index: 724140 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.8033. Min Act: -0.0000

Data Index: 967772 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.8102. Min Act: -0.0000

Data Index: 871205 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1304167 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.8409. Min Act: -0.0000

Data Index: 210839 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.8337. Min Act: -0.0000

Data Index: 1036827 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.8182. Min Act: -0.0000

Data Index: 927654 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.7535. Min Act: -0.0000

Data Index: 89755 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1260381 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.7687. Min Act: -0.0000

Data Index: 1012515 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.6930. Min Act: -0.0000

Data Index: 346991 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.7421. Min Act: -0.0000

Data Index: 917831 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.6870. Min Act: -0.0000

Data Index: 394504 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.7077. Min Act: -0.0000

Data Index: 124674 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.7104. Min Act: -0.0000

Data Index: 297937 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.7159. Min Act: -0.0000

Data Index: 806855 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 0.9070. Min Range: -0.9070

Max Act: 0.7090. Min Act: -0.0000

Data Index: 1267772 (C4 (Web Text))

Max Activating Token Index: 731