Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2111 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.8835. Min Act: -0.0001

Data Index: 537937 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7301. Min Act: -0.0001

Data Index: 81942 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6972. Min Act: -0.0001

Data Index: 846316 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7444. Min Act: -0.0001

Data Index: 338422 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7632. Min Act: -0.0001

Data Index: 165772 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7433. Min Act: -0.0001

Data Index: 61687 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7000. Min Act: -0.0001

Data Index: 1080742 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7696. Min Act: -0.0001

Data Index: 690210 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7870. Min Act: -0.0001

Data Index: 24870 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6834. Min Act: -0.0001

Data Index: 767833 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6614. Min Act: -0.0001

Data Index: 20106 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6619. Min Act: -0.0001

Data Index: 656336 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7372. Min Act: -0.0001

Data Index: 1284873 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7159. Min Act: -0.0001

Data Index: 242860 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6691. Min Act: -0.0001

Data Index: 829055 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6678. Min Act: -0.0001

Data Index: 479388 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6796. Min Act: -0.0001

Data Index: 1121810 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6813. Min Act: -0.0001

Data Index: 164433 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6586. Min Act: -0.0001

Data Index: 568767 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6590. Min Act: -0.0001

Data Index: 442861 (C4 (Web Text))

Max Activating Token Index: 850