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

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

Neuron 5616 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7682. Min Range: -0.7682

Max Act: 0.7682. Min Act: -0.0000

Data Index: 1244594 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.7682. Min Range: -0.7682

Max Act: 0.7315. Min Act: -0.0000

Data Index: 623533 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.7682. Min Range: -0.7682

Max Act: 0.6670. Min Act: -0.0000

Data Index: 1087513 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.7682. Min Range: -0.7682

Max Act: 0.7042. Min Act: -0.0000

Data Index: 1014694 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.7682. Min Range: -0.7682

Max Act: 0.6946. Min Act: -0.0000

Data Index: 727879 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.7682. Min Range: -0.7682

Max Act: 0.6188. Min Act: -0.0000

Data Index: 360524 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 0.7682. Min Range: -0.7682

Max Act: 0.6360. Min Act: -0.0000

Data Index: 959317 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.7682. Min Range: -0.7682

Max Act: 0.6651. Min Act: -0.0000

Data Index: 526880 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 0.7682. Min Range: -0.7682

Max Act: 0.6520. Min Act: -0.0000

Data Index: 1018953 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.7682. Min Range: -0.7682

Max Act: 0.6696. Min Act: -0.0000

Data Index: 5 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.7682. Min Range: -0.7682

Max Act: 0.5808. Min Act: -0.0000

Data Index: 437299 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.7682. Min Range: -0.7682

Max Act: 0.5709. Min Act: -0.0000

Data Index: 845279 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.7682. Min Range: -0.7682

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1477402 (Python Code)

Max Activating Token Index: 185

Text #13

Max Range: 0.7682. Min Range: -0.7682

Max Act: 0.5491. Min Act: -0.0000

Data Index: 841045 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 0.7682. Min Range: -0.7682

Max Act: 0.5341. Min Act: -0.0000

Data Index: 1324879 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.7682. Min Range: -0.7682

Max Act: 0.5086. Min Act: -0.0000

Data Index: 1649882 (Python Code)

Max Activating Token Index: 212

Text #16

Max Range: 0.7682. Min Range: -0.7682

Max Act: 0.4795. Min Act: -0.0000

Data Index: 547797 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.7682. Min Range: -0.7682

Max Act: 0.4721. Min Act: -0.0000

Data Index: 296824 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.7682. Min Range: -0.7682

Max Act: 0.5128. Min Act: -0.0000

Data Index: 777459 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.7682. Min Range: -0.7682

Max Act: 0.4968. Min Act: 0.0000

Data Index: 1043077 (C4 (Web Text))

Max Activating Token Index: 165