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

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

Neuron 2447 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.4455. Min Act: -0.0001

Data Index: 427489 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.4287. Min Act: -0.0001

Data Index: 644249 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.4126. Min Act: -0.0001

Data Index: 559941 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.4131. Min Act: -0.0001

Data Index: 1248355 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3901. Min Act: -0.0001

Data Index: 595107 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.4044. Min Act: -0.0001

Data Index: 1513384 (Python Code)

Max Activating Token Index: 846

Text #6

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3886. Min Act: -0.0001

Data Index: 317922 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3892. Min Act: -0.0001

Data Index: 178744 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3760. Min Act: -0.0001

Data Index: 122879 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3892. Min Act: -0.0001

Data Index: 1065630 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3808. Min Act: -0.0001

Data Index: 1327323 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3793. Min Act: -0.0001

Data Index: 1151385 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3895. Min Act: -0.0001

Data Index: 485006 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3631. Min Act: -0.0001

Data Index: 671122 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3762. Min Act: -0.0001

Data Index: 435561 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3836. Min Act: -0.0001

Data Index: 317518 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3488. Min Act: -0.0001

Data Index: 579014 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3851. Min Act: -0.0001

Data Index: 974633 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3686. Min Act: -0.0001

Data Index: 77429 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3815. Min Act: -0.0001

Data Index: 941106 (C4 (Web Text))

Max Activating Token Index: 221