Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5202 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4529. Min Range: -0.4529

Max Act: 0.4521. Min Act: -0.0000

Data Index: 753843 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 0.4529. Min Range: -0.4529

Max Act: 0.4011. Min Act: -0.0000

Data Index: 943112 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 0.4529. Min Range: -0.4529

Max Act: 0.4529. Min Act: -0.0000

Data Index: 552506 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 0.4529. Min Range: -0.4529

Max Act: 0.4251. Min Act: -0.0000

Data Index: 142185 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.4529. Min Range: -0.4529

Max Act: 0.4415. Min Act: -0.0000

Data Index: 293791 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 0.4529. Min Range: -0.4529

Max Act: 0.3621. Min Act: -0.0000

Data Index: 312044 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 0.4529. Min Range: -0.4529

Max Act: 0.4163. Min Act: -0.0000

Data Index: 916038 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.4529. Min Range: -0.4529

Max Act: 0.3914. Min Act: -0.0000

Data Index: 384182 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.4529. Min Range: -0.4529

Max Act: 0.3924. Min Act: -0.0000

Data Index: 825726 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.4529. Min Range: -0.4529

Max Act: 0.3877. Min Act: -0.0000

Data Index: 528262 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.4529. Min Range: -0.4529

Max Act: 0.3616. Min Act: -0.0000

Data Index: 667388 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 0.4529. Min Range: -0.4529

Max Act: 0.3859. Min Act: -0.0000

Data Index: 1012956 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 0.4529. Min Range: -0.4529

Max Act: 0.3922. Min Act: -0.0000

Data Index: 505554 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.4529. Min Range: -0.4529

Max Act: 0.3655. Min Act: -0.0000

Data Index: 1089496 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.4529. Min Range: -0.4529

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1127144 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.4529. Min Range: -0.4529

Max Act: 0.3712. Min Act: -0.0000

Data Index: 379823 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 0.4529. Min Range: -0.4529

Max Act: 0.3682. Min Act: -0.0000

Data Index: 1289174 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.4529. Min Range: -0.4529

Max Act: 0.3673. Min Act: -0.0000

Data Index: 292617 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.4529. Min Range: -0.4529

Max Act: 0.3680. Min Act: -0.0000

Data Index: 259947 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.4529. Min Range: -0.4529

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1126783 (C4 (Web Text))

Max Activating Token Index: 243