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

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

Neuron 1919 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.6529. Min Act: -0.0000

Data Index: 1285492 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.5289. Min Act: -0.0000

Data Index: 890538 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.3817. Min Act: -0.0000

Data Index: 978145 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.4266. Min Act: -0.0000

Data Index: 410913 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.3600. Min Act: -0.0000

Data Index: 498519 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.3911. Min Act: -0.0000

Data Index: 348097 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.4248. Min Act: -0.0000

Data Index: 72849 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.3163. Min Act: -0.0000

Data Index: 1162962 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.3063. Min Act: -0.0000

Data Index: 358984 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.4096. Min Act: -0.0000

Data Index: 996419 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.2817. Min Act: -0.0000

Data Index: 1291266 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.2373. Min Act: -0.0000

Data Index: 1096486 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.2530. Min Act: -0.0000

Data Index: 1340318 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.2502. Min Act: -0.0000

Data Index: 1484202 (Python Code)

Max Activating Token Index: 827

Text #14

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.2532. Min Act: -0.0000

Data Index: 1552684 (Python Code)

Max Activating Token Index: 135

Text #15

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.2851. Min Act: -0.0000

Data Index: 591075 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.2205. Min Act: -0.0000

Data Index: 1090871 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.2606. Min Act: -0.0000

Data Index: 427694 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.1297. Min Act: -0.0000

Data Index: 1312094 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 1.6529. Min Range: -1.6529

Max Act: 1.1569. Min Act: -0.0000

Data Index: 1057009 (C4 (Web Text))

Max Activating Token Index: 983