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

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

Neuron 5518 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.2968. Min Act: -0.0000

Data Index: 92891 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.1816. Min Act: -0.0000

Data Index: 45548 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.2493. Min Act: -0.0000

Data Index: 1308685 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.1563. Min Act: -0.0000

Data Index: 367569 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.1402. Min Act: -0.0000

Data Index: 16422 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.1098. Min Act: -0.0000

Data Index: 263287 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.0359. Min Act: -0.0000

Data Index: 750166 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.0574. Min Act: -0.0000

Data Index: 814944 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.9448. Min Act: -0.0000

Data Index: 712388 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.9183. Min Act: -0.0000

Data Index: 359510 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.0029. Min Act: -0.0000

Data Index: 722103 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.9390. Min Act: -0.0000

Data Index: 813648 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.8983. Min Act: -0.0000

Data Index: 1200840 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.8973. Min Act: -0.0000

Data Index: 810427 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.9583. Min Act: -0.0000

Data Index: 1169404 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.8288. Min Act: -0.0000

Data Index: 944688 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.8206. Min Act: -0.0000

Data Index: 575781 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.8353. Min Act: -0.0000

Data Index: 999359 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.8850. Min Act: -0.0000

Data Index: 743911 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.7306. Min Act: -0.0000

Data Index: 1266828 (C4 (Web Text))

Max Activating Token Index: 382