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

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

Neuron 2675 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: 1.3038. Min Range: -1.3038

Max Act: 1.3038. Min Act: -0.0000

Data Index: 460598 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 1.3038. Min Range: -1.3038

Max Act: 1.1877. Min Act: -0.0000

Data Index: 110828 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 1.3038. Min Range: -1.3038

Max Act: 0.8496. Min Act: -0.0000

Data Index: 654825 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 1.3038. Min Range: -1.3038

Max Act: 0.8330. Min Act: -0.0000

Data Index: 85349 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 1.3038. Min Range: -1.3038

Max Act: 0.7810. Min Act: -0.0000

Data Index: 947921 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 1.3038. Min Range: -1.3038

Max Act: 0.7565. Min Act: -0.0000

Data Index: 541976 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 1.3038. Min Range: -1.3038

Max Act: 0.7901. Min Act: -0.0000

Data Index: 1200497 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 1.3038. Min Range: -1.3038

Max Act: 0.7174. Min Act: -0.0000

Data Index: 114445 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 1.3038. Min Range: -1.3038

Max Act: 0.7288. Min Act: -0.0000

Data Index: 1271343 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 1.3038. Min Range: -1.3038

Max Act: 0.6915. Min Act: -0.0000

Data Index: 344352 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 1.3038. Min Range: -1.3038

Max Act: 0.7096. Min Act: -0.0000

Data Index: 1099038 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 1.3038. Min Range: -1.3038

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1289178 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 1.3038. Min Range: -1.3038

Max Act: 0.6532. Min Act: -0.0000

Data Index: 274461 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 1.3038. Min Range: -1.3038

Max Act: 0.6896. Min Act: -0.0000

Data Index: 254129 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 1.3038. Min Range: -1.3038

Max Act: 0.6437. Min Act: -0.0000

Data Index: 459766 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 1.3038. Min Range: -1.3038

Max Act: 0.6357. Min Act: -0.0000

Data Index: 1225691 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 1.3038. Min Range: -1.3038

Max Act: 0.6515. Min Act: -0.0000

Data Index: 410226 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 1.3038. Min Range: -1.3038

Max Act: 0.6245. Min Act: -0.0000

Data Index: 45874 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 1.3038. Min Range: -1.3038

Max Act: 0.6203. Min Act: -0.0000

Data Index: 1258135 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 1.3038. Min Range: -1.3038

Max Act: 0.6408. Min Act: -0.0000

Data Index: 628326 (C4 (Web Text))

Max Activating Token Index: 68