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

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

Neuron 1692 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.9553. Min Act: -0.0001

Data Index: 1105162 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.9662. Min Act: -0.0001

Data Index: 995838 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.8611. Min Act: -0.0001

Data Index: 853981 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.8131. Min Act: -0.0001

Data Index: 1320147 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.9059. Min Act: -0.0001

Data Index: 199543 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.8489. Min Act: -0.0001

Data Index: 371949 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.8266. Min Act: -0.0001

Data Index: 1280920 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.7619. Min Act: -0.0001

Data Index: 265591 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.7836. Min Act: -0.0001

Data Index: 744406 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.7838. Min Act: -0.0001

Data Index: 381463 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.7966. Min Act: -0.0001

Data Index: 1263442 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.7681. Min Act: -0.0001

Data Index: 581776 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.7551. Min Act: -0.0001

Data Index: 357246 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.7160. Min Act: -0.0001

Data Index: 763562 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.7642. Min Act: -0.0001

Data Index: 1046619 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.6995. Min Act: -0.0001

Data Index: 15673 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.6734. Min Act: -0.0001

Data Index: 349196 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.6305. Min Act: -0.0001

Data Index: 624066 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.6644. Min Act: -0.0001

Data Index: 257011 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.9662. Min Range: -0.9662

Max Act: 0.6374. Min Act: -0.0001

Data Index: 1114826 (C4 (Web Text))

Max Activating Token Index: 617