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

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

Neuron 3029 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: 1.1733. Min Range: -1.1733

Max Act: 1.1733. Min Act: -0.0002

Data Index: 897846 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 1.1733. Min Range: -1.1733

Max Act: 0.8294. Min Act: -0.0001

Data Index: 884507 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 1.1733. Min Range: -1.1733

Max Act: 0.8115. Min Act: -0.0001

Data Index: 744314 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 1.1733. Min Range: -1.1733

Max Act: 0.8366. Min Act: -0.0002

Data Index: 343343 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 1.1733. Min Range: -1.1733

Max Act: 0.8004. Min Act: -0.0001

Data Index: 649242 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 1.1733. Min Range: -1.1733

Max Act: 0.8464. Min Act: -0.0001

Data Index: 64229 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 1.1733. Min Range: -1.1733

Max Act: 0.8170. Min Act: -0.0001

Data Index: 778594 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 1.1733. Min Range: -1.1733

Max Act: 0.8191. Min Act: -0.0002

Data Index: 265131 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 1.1733. Min Range: -1.1733

Max Act: 0.8144. Min Act: -0.0002

Data Index: 410279 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 1.1733. Min Range: -1.1733

Max Act: 0.8155. Min Act: -0.0001

Data Index: 66997 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 1.1733. Min Range: -1.1733

Max Act: 0.8090. Min Act: -0.0001

Data Index: 787091 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 1.1733. Min Range: -1.1733

Max Act: 0.7689. Min Act: -0.0002

Data Index: 232883 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 1.1733. Min Range: -1.1733

Max Act: 0.7860. Min Act: -0.0002

Data Index: 165108 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 1.1733. Min Range: -1.1733

Max Act: 0.7838. Min Act: -0.0001

Data Index: 426920 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 1.1733. Min Range: -1.1733

Max Act: 0.7533. Min Act: -0.0001

Data Index: 1156575 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 1.1733. Min Range: -1.1733

Max Act: 0.7464. Min Act: -0.0001

Data Index: 748229 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 1.1733. Min Range: -1.1733

Max Act: 0.7944. Min Act: -0.0001

Data Index: 296558 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 1.1733. Min Range: -1.1733

Max Act: 0.7916. Min Act: -0.0002

Data Index: 238953 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 1.1733. Min Range: -1.1733

Max Act: 0.7396. Min Act: -0.0002

Data Index: 4274 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 1.1733. Min Range: -1.1733

Max Act: 0.7626. Min Act: -0.0002

Data Index: 977319 (C4 (Web Text))

Max Activating Token Index: 347