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

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

Neuron 685 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.6071. Min Act: -0.0001

Data Index: 41212 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.6201. Min Act: -0.0001

Data Index: 18391 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5843. Min Act: -0.0001

Data Index: 149227 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5596. Min Act: -0.0001

Data Index: 14834 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5572. Min Act: -0.0001

Data Index: 366723 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5502. Min Act: -0.0001

Data Index: 766683 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5083. Min Act: -0.0001

Data Index: 866945 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5238. Min Act: -0.0001

Data Index: 113739 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4951. Min Act: -0.0001

Data Index: 645931 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5062. Min Act: -0.0001

Data Index: 296427 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5036. Min Act: -0.0001

Data Index: 595360 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5181. Min Act: -0.0001

Data Index: 280553 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4819. Min Act: -0.0001

Data Index: 284448 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5153. Min Act: -0.0001

Data Index: 651598 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4634. Min Act: -0.0001

Data Index: 127986 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4922. Min Act: -0.0001

Data Index: 277874 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4903. Min Act: -0.0001

Data Index: 242120 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4892. Min Act: -0.0001

Data Index: 234050 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4698. Min Act: -0.0001

Data Index: 367864 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.4810. Min Act: -0.0001

Data Index: 1057707 (C4 (Web Text))

Max Activating Token Index: 412