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

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

Neuron 4582 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: 0.9220. Min Range: -0.9220

Max Act: 0.9084. Min Act: -0.0000

Data Index: 1127466 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.9220. Min Act: -0.0000

Data Index: 867740 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.8660. Min Act: -0.0000

Data Index: 478858 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.8202. Min Act: -0.0000

Data Index: 550959 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7332. Min Act: -0.0000

Data Index: 665634 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7754. Min Act: -0.0000

Data Index: 1001440 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7373. Min Act: 0.0000

Data Index: 555919 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7392. Min Act: -0.0000

Data Index: 460194 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7058. Min Act: -0.0000

Data Index: 866677 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7177. Min Act: 0.0000

Data Index: 152586 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7423. Min Act: -0.0000

Data Index: 1013747 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7122. Min Act: -0.0000

Data Index: 792283 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.7008. Min Act: -0.0000

Data Index: 862409 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1121713 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1207845 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1105983 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.6466. Min Act: -0.0000

Data Index: 186791 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.6871. Min Act: -0.0000

Data Index: 1154255 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.6135. Min Act: -0.0000

Data Index: 184679 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.9220. Min Range: -0.9220

Max Act: 0.6097. Min Act: 0.0000

Data Index: 70658 (C4 (Web Text))

Max Activating Token Index: 144