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

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

Neuron 1585 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.9420. Min Act: -0.0001

Data Index: 865127 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.1607. Min Act: -0.0001

Data Index: 144053 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.1945. Min Act: -0.0001

Data Index: 1291598 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.0163. Min Act: -0.0001

Data Index: 177229 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 3.9420. Min Range: -3.9420

Max Act: 3.0011. Min Act: -0.0001

Data Index: 277079 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 3.9420. Min Range: -3.9420

Max Act: 2.9777. Min Act: -0.0001

Data Index: 377773 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 3.9420. Min Range: -3.9420

Max Act: 2.9572. Min Act: -0.0001

Data Index: 489349 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 3.9420. Min Range: -3.9420

Max Act: 2.9056. Min Act: -0.0001

Data Index: 1027885 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 3.9420. Min Range: -3.9420

Max Act: 2.7034. Min Act: -0.0001

Data Index: 1181531 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 3.9420. Min Range: -3.9420

Max Act: 2.6629. Min Act: -0.0001

Data Index: 360267 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 3.9420. Min Range: -3.9420

Max Act: 2.7143. Min Act: -0.0001

Data Index: 856386 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 3.9420. Min Range: -3.9420

Max Act: 2.5896. Min Act: -0.0001

Data Index: 565616 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 3.9420. Min Range: -3.9420

Max Act: 2.5432. Min Act: -0.0001

Data Index: 1299113 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 3.9420. Min Range: -3.9420

Max Act: 2.5165. Min Act: -0.0001

Data Index: 674007 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 3.9420. Min Range: -3.9420

Max Act: 2.4647. Min Act: -0.0001

Data Index: 98809 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 3.9420. Min Range: -3.9420

Max Act: 2.3304. Min Act: -0.0001

Data Index: 441977 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 3.9420. Min Range: -3.9420

Max Act: 2.3029. Min Act: -0.0001

Data Index: 461726 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 3.9420. Min Range: -3.9420

Max Act: 2.4197. Min Act: -0.0001

Data Index: 606247 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 3.9420. Min Range: -3.9420

Max Act: 2.5434. Min Act: -0.0001

Data Index: 1336318 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 3.9420. Min Range: -3.9420

Max Act: 2.4237. Min Act: -0.0001

Data Index: 373622 (C4 (Web Text))

Max Activating Token Index: 756