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

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

Neuron 3038 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.7374. Min Act: -0.0000

Data Index: 941107 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.7174. Min Act: -0.0000

Data Index: 475617 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.6732. Min Act: -0.0000

Data Index: 683022 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.6148. Min Act: -0.0000

Data Index: 900186 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5833. Min Act: -0.0000

Data Index: 1064687 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5582. Min Act: -0.0000

Data Index: 379026 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5924. Min Act: -0.0000

Data Index: 1318758 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5770. Min Act: -0.0000

Data Index: 566281 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5332. Min Act: -0.0000

Data Index: 262927 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5150. Min Act: -0.0000

Data Index: 94895 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5379. Min Act: -0.0000

Data Index: 189929 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5142. Min Act: -0.0000

Data Index: 38054 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5011. Min Act: -0.0000

Data Index: 254997 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.4954. Min Act: -0.0000

Data Index: 692955 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5050. Min Act: -0.0000

Data Index: 872434 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5007. Min Act: -0.0000

Data Index: 665914 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.4818. Min Act: -0.0000

Data Index: 666800 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.4944. Min Act: -0.0000

Data Index: 93066 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.4820. Min Act: -0.0000

Data Index: 318706 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 0.7374. Min Range: -0.7374

Max Act: 0.5011. Min Act: -0.0000

Data Index: 343769 (C4 (Web Text))

Max Activating Token Index: 104