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

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

Neuron 317 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.8499. Min Act: -0.0001

Data Index: 845260 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.7202. Min Act: -0.0001

Data Index: 461745 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6443. Min Act: -0.0001

Data Index: 514894 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6447. Min Act: -0.0001

Data Index: 338757 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6076. Min Act: -0.0001

Data Index: 922164 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6466. Min Act: -0.0000

Data Index: 749 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6431. Min Act: -0.0001

Data Index: 1294855 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.5730. Min Act: -0.0001

Data Index: 427180 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6150. Min Act: -0.0001

Data Index: 814264 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6117. Min Act: 0.0000

Data Index: 477865 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6022. Min Act: -0.0001

Data Index: 1009984 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.5981. Min Act: -0.0001

Data Index: 540515 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6179. Min Act: -0.0001

Data Index: 921970 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.5715. Min Act: -0.0001

Data Index: 100293 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.5889. Min Act: 0.0001

Data Index: 369725 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.5873. Min Act: -0.0001

Data Index: 713385 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.6026. Min Act: -0.0001

Data Index: 215871 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.5736. Min Act: -0.0000

Data Index: 82328 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.5585. Min Act: -0.0001

Data Index: 634757 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.5942. Min Act: -0.0000

Data Index: 467548 (C4 (Web Text))

Max Activating Token Index: 578