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

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

Neuron 1117 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9386. Min Range: -1.9386

Max Act: 1.9386. Min Act: -0.0001

Data Index: 531194 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 1.9386. Min Range: -1.9386

Max Act: 1.6964. Min Act: -0.0001

Data Index: 148171 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 1.9386. Min Range: -1.9386

Max Act: 1.6575. Min Act: -0.0001

Data Index: 1096634 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 1.9386. Min Range: -1.9386

Max Act: 1.7082. Min Act: -0.0001

Data Index: 476260 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 1.9386. Min Range: -1.9386

Max Act: 1.5204. Min Act: -0.0001

Data Index: 407964 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 1.9386. Min Range: -1.9386

Max Act: 1.6325. Min Act: -0.0001

Data Index: 1177801 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 1.9386. Min Range: -1.9386

Max Act: 1.4616. Min Act: -0.0001

Data Index: 41010 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 1.9386. Min Range: -1.9386

Max Act: 1.4134. Min Act: -0.0001

Data Index: 428436 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 1.9386. Min Range: -1.9386

Max Act: 1.5351. Min Act: -0.0001

Data Index: 350852 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 1.9386. Min Range: -1.9386

Max Act: 1.4507. Min Act: -0.0001

Data Index: 323484 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 1.9386. Min Range: -1.9386

Max Act: 1.4101. Min Act: -0.0001

Data Index: 213112 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 1.9386. Min Range: -1.9386

Max Act: 1.4078. Min Act: -0.0001

Data Index: 1524579 (Python Code)

Max Activating Token Index: 627

Text #12

Max Range: 1.9386. Min Range: -1.9386

Max Act: 1.3863. Min Act: -0.0001

Data Index: 444946 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 1.9386. Min Range: -1.9386

Max Act: 1.3618. Min Act: -0.0001

Data Index: 207364 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 1.9386. Min Range: -1.9386

Max Act: 1.3670. Min Act: -0.0001

Data Index: 955802 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 1.9386. Min Range: -1.9386

Max Act: 1.3705. Min Act: -0.0001

Data Index: 243406 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 1.9386. Min Range: -1.9386

Max Act: 1.3447. Min Act: -0.0001

Data Index: 830376 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 1.9386. Min Range: -1.9386

Max Act: 1.3413. Min Act: -0.0001

Data Index: 621108 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 1.9386. Min Range: -1.9386

Max Act: 1.3818. Min Act: -0.0001

Data Index: 602700 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 1.9386. Min Range: -1.9386

Max Act: 1.3243. Min Act: -0.0001

Data Index: 860708 (C4 (Web Text))

Max Activating Token Index: 336