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

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

Neuron 3320 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: 0.8592. Min Range: -0.8592

Max Act: 0.8592. Min Act: -0.0002

Data Index: 943206 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.8041. Min Act: -0.0002

Data Index: 790722 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7972. Min Act: -0.0002

Data Index: 840091 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7904. Min Act: -0.0002

Data Index: 426038 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7880. Min Act: -0.0002

Data Index: 217824 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.8011. Min Act: -0.0002

Data Index: 1348524 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7983. Min Act: -0.0002

Data Index: 949277 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7739. Min Act: -0.0002

Data Index: 1164545 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7717. Min Act: -0.0002

Data Index: 691285 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7717. Min Act: -0.0002

Data Index: 1140764 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7784. Min Act: -0.0002

Data Index: 1169315 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7584. Min Act: -0.0002

Data Index: 740756 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7736. Min Act: -0.0002

Data Index: 952106 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7624. Min Act: -0.0002

Data Index: 70763 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7517. Min Act: -0.0002

Data Index: 525557 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7463. Min Act: -0.0002

Data Index: 1093825 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7454. Min Act: -0.0002

Data Index: 462428 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7663. Min Act: -0.0002

Data Index: 1092570 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7617. Min Act: -0.0002

Data Index: 804163 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7584. Min Act: -0.0002

Data Index: 20250 (C4 (Web Text))

Max Activating Token Index: 893