Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4909 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8595. Min Range: -2.8595

Max Act: 2.8595. Min Act: -0.0000

Data Index: 220605 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 2.8595. Min Range: -2.8595

Max Act: 2.2921. Min Act: -0.0000

Data Index: 1121789 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 2.8595. Min Range: -2.8595

Max Act: 1.9838. Min Act: -0.0000

Data Index: 1085673 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 2.8595. Min Range: -2.8595

Max Act: 1.9557. Min Act: -0.0000

Data Index: 568264 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 2.8595. Min Range: -2.8595

Max Act: 1.8273. Min Act: -0.0000

Data Index: 316547 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 2.8595. Min Range: -2.8595

Max Act: 1.8471. Min Act: -0.0000

Data Index: 406601 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 2.8595. Min Range: -2.8595

Max Act: 1.7874. Min Act: -0.0000

Data Index: 176299 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 2.8595. Min Range: -2.8595

Max Act: 1.7091. Min Act: -0.0000

Data Index: 1042644 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 2.8595. Min Range: -2.8595

Max Act: 1.6976. Min Act: -0.0000

Data Index: 586433 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 2.8595. Min Range: -2.8595

Max Act: 1.8318. Min Act: -0.0000

Data Index: 1108497 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 2.8595. Min Range: -2.8595

Max Act: 1.7668. Min Act: -0.0000

Data Index: 313033 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 2.8595. Min Range: -2.8595

Max Act: 1.7699. Min Act: -0.0000

Data Index: 506058 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 2.8595. Min Range: -2.8595

Max Act: 1.7886. Min Act: -0.0000

Data Index: 130155 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 2.8595. Min Range: -2.8595

Max Act: 1.7121. Min Act: -0.0000

Data Index: 965344 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 2.8595. Min Range: -2.8595

Max Act: 1.7051. Min Act: -0.0000

Data Index: 288676 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 2.8595. Min Range: -2.8595

Max Act: 1.6801. Min Act: -0.0000

Data Index: 857113 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 2.8595. Min Range: -2.8595

Max Act: 1.6335. Min Act: -0.0000

Data Index: 1108242 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 2.8595. Min Range: -2.8595

Max Act: 1.6979. Min Act: -0.0000

Data Index: 360618 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 2.8595. Min Range: -2.8595

Max Act: 1.7064. Min Act: -0.0000

Data Index: 867032 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 2.8595. Min Range: -2.8595

Max Act: 1.5637. Min Act: -0.0000

Data Index: 283583 (C4 (Web Text))

Max Activating Token Index: 111