Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 533 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.9537. Min Act: -0.0001

Data Index: 324715 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.7365. Min Act: -0.0001

Data Index: 283716 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.8611. Min Act: -0.0001

Data Index: 461619 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.6409. Min Act: -0.0001

Data Index: 1083028 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.6511. Min Act: -0.0001

Data Index: 766014 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.6197. Min Act: -0.0001

Data Index: 402849 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.6964. Min Act: -0.0001

Data Index: 433076 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.5407. Min Act: -0.0001

Data Index: 68809 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.6788. Min Act: -0.0001

Data Index: 581039 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.5885. Min Act: -0.0001

Data Index: 680169 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.4880. Min Act: -0.0001

Data Index: 196865 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.3063. Min Act: -0.0001

Data Index: 446210 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.5668. Min Act: -0.0001

Data Index: 620262 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.4055. Min Act: -0.0001

Data Index: 473315 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.5034. Min Act: -0.0001

Data Index: 568229 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.4078. Min Act: -0.0001

Data Index: 965288 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.3736. Min Act: -0.0001

Data Index: 720507 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.3356. Min Act: -0.0001

Data Index: 732563 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.3644. Min Act: -0.0001

Data Index: 1171539 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.3176. Min Act: -0.0001

Data Index: 155606 (C4 (Web Text))

Max Activating Token Index: 930