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

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

Neuron 4508 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.5509. Min Act: -0.0002

Data Index: 1154477 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.5529. Min Act: -0.0002

Data Index: 977894 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.5428. Min Act: -0.0002

Data Index: 247544 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.5136. Min Act: -0.0002

Data Index: 184276 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4953. Min Act: -0.0002

Data Index: 883629 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4874. Min Act: -0.0002

Data Index: 433070 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4890. Min Act: -0.0002

Data Index: 998062 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4870. Min Act: -0.0002

Data Index: 60295 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4790. Min Act: -0.0002

Data Index: 413297 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4883. Min Act: -0.0002

Data Index: 1019269 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4693. Min Act: -0.0002

Data Index: 406087 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4621. Min Act: -0.0002

Data Index: 1038679 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4666. Min Act: -0.0002

Data Index: 751670 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4598. Min Act: -0.0002

Data Index: 1008085 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4614. Min Act: -0.0002

Data Index: 782503 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4725. Min Act: -0.0002

Data Index: 997922 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4602. Min Act: -0.0002

Data Index: 1125415 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4560. Min Act: -0.0002

Data Index: 738071 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4526. Min Act: -0.0002

Data Index: 1119076 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.5529. Min Range: -0.5529

Max Act: 0.4496. Min Act: -0.0002

Data Index: 813679 (C4 (Web Text))

Max Activating Token Index: 85