Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3306 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.9407. Min Act: -0.0001

Data Index: 1314704 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.8764. Min Act: -0.0001

Data Index: 1170900 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.8236. Min Act: -0.0001

Data Index: 1017624 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.9927. Min Act: -0.0001

Data Index: 111005 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.8329. Min Act: -0.0001

Data Index: 184593 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7331. Min Act: -0.0002

Data Index: 46833 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7970. Min Act: -0.0001

Data Index: 1102525 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7529. Min Act: -0.0001

Data Index: 1229861 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7513. Min Act: -0.0002

Data Index: 60005 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7595. Min Act: -0.0001

Data Index: 683447 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7350. Min Act: -0.0001

Data Index: 349345 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7745. Min Act: -0.0001

Data Index: 907119 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7884. Min Act: -0.0002

Data Index: 108750 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6998. Min Act: -0.0002

Data Index: 51034 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7141. Min Act: -0.0002

Data Index: 1003495 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7195. Min Act: -0.0002

Data Index: 1213515 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7522. Min Act: -0.0001

Data Index: 165939 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7313. Min Act: -0.0001

Data Index: 591375 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.6923. Min Act: -0.0002

Data Index: 1212281 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7729. Min Act: -0.0001

Data Index: 302996 (C4 (Web Text))

Max Activating Token Index: 525