Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2804 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.9650. Min Act: -0.0001

Data Index: 1175550 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.9217. Min Act: -0.0001

Data Index: 115255 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.9193. Min Act: -0.0001

Data Index: 142231 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.9197. Min Act: -0.0001

Data Index: 1157145 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.8838. Min Act: -0.0001

Data Index: 617117 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 1.0572. Min Range: -1.0572

Max Act: 1.0572. Min Act: -0.0001

Data Index: 557476 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 1.0572. Min Range: -1.0572

Max Act: 1.0211. Min Act: -0.0001

Data Index: 611366 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.8974. Min Act: -0.0001

Data Index: 594409 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.8322. Min Act: -0.0001

Data Index: 49247 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.7479. Min Act: -0.0001

Data Index: 388326 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.6546. Min Act: -0.0001

Data Index: 1050384 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.6957. Min Act: -0.0001

Data Index: 511162 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.7054. Min Act: -0.0001

Data Index: 370506 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.7002. Min Act: -0.0001

Data Index: 878847 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.6468. Min Act: -0.0001

Data Index: 455307 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.6334. Min Act: -0.0001

Data Index: 1072412 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.6357. Min Act: -0.0001

Data Index: 8696 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.6458. Min Act: -0.0001

Data Index: 97723 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.5481. Min Act: -0.0001

Data Index: 333208 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 1.0572. Min Range: -1.0572

Max Act: 0.5923. Min Act: -0.0001

Data Index: 118975 (C4 (Web Text))

Max Activating Token Index: 703