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

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

Neuron 4994 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0886. Min Range: -1.0886

Max Act: 1.0886. Min Act: -0.0000

Data Index: 496897 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 1.0886. Min Range: -1.0886

Max Act: 1.0815. Min Act: -0.0000

Data Index: 474150 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.9876. Min Act: -0.0000

Data Index: 386162 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 1.0886. Min Range: -1.0886

Max Act: 1.0061. Min Act: -0.0000

Data Index: 860530 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.9915. Min Act: -0.0000

Data Index: 942072 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 1.0886. Min Range: -1.0886

Max Act: 1.0518. Min Act: -0.0000

Data Index: 819386 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 1.0886. Min Range: -1.0886

Max Act: 1.0051. Min Act: -0.0000

Data Index: 715062 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.9400. Min Act: -0.0000

Data Index: 501556 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.9241. Min Act: -0.0000

Data Index: 533386 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.9441. Min Act: -0.0000

Data Index: 654674 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.8908. Min Act: -0.0000

Data Index: 460222 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.8954. Min Act: -0.0000

Data Index: 1104201 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.9042. Min Act: -0.0000

Data Index: 625548 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.8669. Min Act: -0.0000

Data Index: 398032 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.8088. Min Act: -0.0000

Data Index: 307991 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.8866. Min Act: -0.0000

Data Index: 561450 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.8307. Min Act: -0.0000

Data Index: 508946 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.8257. Min Act: -0.0000

Data Index: 736742 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.8557. Min Act: -0.0000

Data Index: 245744 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 1.0886. Min Range: -1.0886

Max Act: 0.8398. Min Act: -0.0000

Data Index: 469317 (C4 (Web Text))

Max Activating Token Index: 989