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

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

Neuron 3406 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: 0.5800. Min Range: -0.5800

Max Act: 0.5800. Min Act: -0.0000

Data Index: 1135264 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.4658. Min Act: -0.0000

Data Index: 684806 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.4311. Min Act: -0.0000

Data Index: 530593 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.4194. Min Act: -0.0000

Data Index: 53951 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.4057. Min Act: -0.0000

Data Index: 506508 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.3931. Min Act: -0.0000

Data Index: 184467 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.3951. Min Act: -0.0000

Data Index: 1068163 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.3778. Min Act: -0.0000

Data Index: 341074 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.3698. Min Act: -0.0000

Data Index: 865937 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.3512. Min Act: -0.0000

Data Index: 194443 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.3418. Min Act: -0.0000

Data Index: 467906 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.3506. Min Act: -0.0000

Data Index: 56203 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.3621. Min Act: -0.0000

Data Index: 25733 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.3369. Min Act: -0.0000

Data Index: 837077 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.3383. Min Act: -0.0000

Data Index: 1287314 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.3352. Min Act: -0.0000

Data Index: 678997 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.3381. Min Act: -0.0000

Data Index: 667416 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.3376. Min Act: -0.0000

Data Index: 1325762 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.3409. Min Act: -0.0000

Data Index: 730383 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.3253. Min Act: -0.0000

Data Index: 1306266 (C4 (Web Text))

Max Activating Token Index: 825