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

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

Neuron 2676 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3018. Min Range: -1.3018

Max Act: 1.3018. Min Act: -0.0001

Data Index: 783863 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 1.3018. Min Range: -1.3018

Max Act: 1.1414. Min Act: -0.0001

Data Index: 201002 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 1.3018. Min Range: -1.3018

Max Act: 1.0573. Min Act: -0.0001

Data Index: 754191 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 1.3018. Min Range: -1.3018

Max Act: 1.1257. Min Act: -0.0001

Data Index: 454977 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.9430. Min Act: -0.0001

Data Index: 489837 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.8716. Min Act: -0.0001

Data Index: 791800 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 1.3018. Min Range: -1.3018

Max Act: 1.0043. Min Act: -0.0001

Data Index: 867778 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.8558. Min Act: -0.0001

Data Index: 1016358 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.8273. Min Act: -0.0001

Data Index: 41460 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.9084. Min Act: -0.0001

Data Index: 1224604 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.8343. Min Act: -0.0001

Data Index: 680385 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.8277. Min Act: -0.0001

Data Index: 821508 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.8374. Min Act: -0.0001

Data Index: 1317123 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.8085. Min Act: -0.0001

Data Index: 567160 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.7898. Min Act: -0.0001

Data Index: 1228700 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.8503. Min Act: -0.0001

Data Index: 105550 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.8420. Min Act: -0.0001

Data Index: 217846 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.8655. Min Act: -0.0001

Data Index: 146360 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.7781. Min Act: -0.0001

Data Index: 294658 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 1.3018. Min Range: -1.3018

Max Act: 0.8098. Min Act: -0.0001

Data Index: 627481 (C4 (Web Text))

Max Activating Token Index: 866