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

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

Neuron 1018 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2035. Min Range: -1.2035

Max Act: 1.2035. Min Act: -0.0000

Data Index: 344935 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9713. Min Act: -0.0000

Data Index: 1205135 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.9509. Min Act: -0.0000

Data Index: 751478 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.8778. Min Act: -0.0001

Data Index: 506479 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.8973. Min Act: -0.0000

Data Index: 366749 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.8863. Min Act: -0.0000

Data Index: 350835 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.7736. Min Act: -0.0000

Data Index: 786250 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.8152. Min Act: -0.0000

Data Index: 1103882 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.8372. Min Act: -0.0000

Data Index: 812800 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.7356. Min Act: -0.0000

Data Index: 1032884 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.7730. Min Act: -0.0001

Data Index: 382650 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.8373. Min Act: -0.0001

Data Index: 745632 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1422213 (Python Code)

Max Activating Token Index: 803

Text #13

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.7933. Min Act: -0.0001

Data Index: 275379 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.6567. Min Act: -0.0000

Data Index: 445634 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.6773. Min Act: -0.0000

Data Index: 491873 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1117323 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.7301. Min Act: -0.0000

Data Index: 726967 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.6740. Min Act: -0.0000

Data Index: 54747 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 1.2035. Min Range: -1.2035

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1081737 (C4 (Web Text))

Max Activating Token Index: 133