Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1434 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3516. Min Act: -0.0001

Data Index: 385342 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3650. Min Act: -0.0001

Data Index: 803605 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3379. Min Act: -0.0001

Data Index: 1066362 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3524. Min Act: -0.0001

Data Index: 1010716 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3024. Min Act: -0.0001

Data Index: 244512 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3258. Min Act: -0.0001

Data Index: 1379484 (Python Code)

Max Activating Token Index: 791

Text #6

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3547. Min Act: -0.0001

Data Index: 357883 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3320. Min Act: -0.0001

Data Index: 1653013 (Python Code)

Max Activating Token Index: 898

Text #8

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3455. Min Act: -0.0001

Data Index: 374721 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3467. Min Act: -0.0001

Data Index: 1586958 (Python Code)

Max Activating Token Index: 657

Text #10

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3445. Min Act: -0.0001

Data Index: 453249 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3337. Min Act: -0.0001

Data Index: 293539 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3532. Min Act: -0.0001

Data Index: 1631366 (Python Code)

Max Activating Token Index: 846

Text #13

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3467. Min Act: -0.0001

Data Index: 353061 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3243. Min Act: -0.0001

Data Index: 146365 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3480. Min Act: -0.0001

Data Index: 716180 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3327. Min Act: -0.0001

Data Index: 1608808 (Python Code)

Max Activating Token Index: 338

Text #17

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3024. Min Act: -0.0001

Data Index: 129415 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3593. Min Act: -0.0001

Data Index: 635428 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2854. Min Act: -0.0001

Data Index: 986064 (C4 (Web Text))

Max Activating Token Index: 663