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

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

Neuron 1034 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.6815. Min Act: -0.0000

Data Index: 1154180 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5999. Min Act: -0.0000

Data Index: 118339 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5823. Min Act: -0.0000

Data Index: 256095 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5363. Min Act: -0.0000

Data Index: 924503 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1000630 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5511. Min Act: -0.0000

Data Index: 1003692 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5130. Min Act: -0.0000

Data Index: 237012 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5442. Min Act: -0.0000

Data Index: 950036 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5323. Min Act: -0.0000

Data Index: 1273774 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5090. Min Act: -0.0000

Data Index: 448202 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1214638 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5226. Min Act: -0.0000

Data Index: 653463 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5439. Min Act: -0.0000

Data Index: 659967 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5051. Min Act: -0.0000

Data Index: 464922 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5104. Min Act: -0.0000

Data Index: 583357 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.4682. Min Act: -0.0000

Data Index: 493258 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.4965. Min Act: -0.0000

Data Index: 583585 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.4622. Min Act: -0.0000

Data Index: 442420 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.4889. Min Act: -0.0000

Data Index: 445634 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.4730. Min Act: -0.0000

Data Index: 128934 (C4 (Web Text))

Max Activating Token Index: 970