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

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

Neuron 1256 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: 0.4595. Min Range: -0.4595

Max Act: 0.4595. Min Act: -0.0000

Data Index: 59388 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 0.4595. Min Range: -0.4595

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1188222 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.4595. Min Range: -0.4595

Max Act: 0.4148. Min Act: -0.0000

Data Index: 684198 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.4595. Min Range: -0.4595

Max Act: 0.4012. Min Act: 0.0000

Data Index: 563923 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.4595. Min Range: -0.4595

Max Act: 0.4149. Min Act: -0.0000

Data Index: 269698 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.4595. Min Range: -0.4595

Max Act: 0.3838. Min Act: -0.0000

Data Index: 880711 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.4595. Min Range: -0.4595

Max Act: 0.3921. Min Act: -0.0000

Data Index: 1374795 (Python Code)

Max Activating Token Index: 698

Text #7

Max Range: 0.4595. Min Range: -0.4595

Max Act: 0.3521. Min Act: -0.0000

Data Index: 1331221 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 0.4595. Min Range: -0.4595

Max Act: 0.3525. Min Act: -0.0000

Data Index: 1011573 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.4595. Min Range: -0.4595

Max Act: 0.3686. Min Act: -0.0000

Data Index: 857260 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 0.4595. Min Range: -0.4595

Max Act: 0.3830. Min Act: -0.0000

Data Index: 451312 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.4595. Min Range: -0.4595

Max Act: 0.3642. Min Act: -0.0000

Data Index: 200817 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.4595. Min Range: -0.4595

Max Act: 0.3477. Min Act: -0.0000

Data Index: 387590 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.4595. Min Range: -0.4595

Max Act: 0.3450. Min Act: -0.0000

Data Index: 571940 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 0.4595. Min Range: -0.4595

Max Act: 0.3723. Min Act: -0.0000

Data Index: 1508119 (Python Code)

Max Activating Token Index: 773

Text #15

Max Range: 0.4595. Min Range: -0.4595

Max Act: 0.3435. Min Act: -0.0000

Data Index: 929190 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 0.4595. Min Range: -0.4595

Max Act: 0.3435. Min Act: -0.0000

Data Index: 1082848 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.4595. Min Range: -0.4595

Max Act: 0.3688. Min Act: -0.0000

Data Index: 254694 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.4595. Min Range: -0.4595

Max Act: 0.3456. Min Act: 0.0000

Data Index: 69216 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.4595. Min Range: -0.4595

Max Act: 0.3232. Min Act: -0.0000

Data Index: 902304 (C4 (Web Text))

Max Activating Token Index: 243