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

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

Neuron 146 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: 1.2921. Min Range: -1.2921

Max Act: 1.2921. Min Act: -0.0000

Data Index: 456369 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 1.2921. Min Range: -1.2921

Max Act: 0.9881. Min Act: -0.0000

Data Index: 1507964 (Python Code)

Max Activating Token Index: 106

Text #2

Max Range: 1.2921. Min Range: -1.2921

Max Act: 0.9222. Min Act: -0.0000

Data Index: 778312 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 1.2921. Min Range: -1.2921

Max Act: 0.7928. Min Act: -0.0000

Data Index: 92256 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 1.2921. Min Range: -1.2921

Max Act: 0.8602. Min Act: -0.0000

Data Index: 648906 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 1.2921. Min Range: -1.2921

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1060407 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 1.2921. Min Range: -1.2921

Max Act: 0.7680. Min Act: -0.0000

Data Index: 291135 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 1.2921. Min Range: -1.2921

Max Act: 0.7920. Min Act: -0.0000

Data Index: 216767 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 1.2921. Min Range: -1.2921

Max Act: 0.7934. Min Act: -0.0000

Data Index: 692305 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 1.2921. Min Range: -1.2921

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1230614 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 1.2921. Min Range: -1.2921

Max Act: 0.7704. Min Act: -0.0000

Data Index: 591672 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 1.2921. Min Range: -1.2921

Max Act: 0.8138. Min Act: -0.0000

Data Index: 42410 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 1.2921. Min Range: -1.2921

Max Act: 0.7342. Min Act: -0.0000

Data Index: 931000 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 1.2921. Min Range: -1.2921

Max Act: 0.6599. Min Act: -0.0000

Data Index: 1152852 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 1.2921. Min Range: -1.2921

Max Act: 0.7640. Min Act: -0.0000

Data Index: 1259930 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 1.2921. Min Range: -1.2921

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1575272 (Python Code)

Max Activating Token Index: 722

Text #16

Max Range: 1.2921. Min Range: -1.2921

Max Act: 0.6492. Min Act: -0.0000

Data Index: 1142757 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 1.2921. Min Range: -1.2921

Max Act: 0.6278. Min Act: -0.0000

Data Index: 799121 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 1.2921. Min Range: -1.2921

Max Act: 0.6565. Min Act: -0.0000

Data Index: 688464 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 1.2921. Min Range: -1.2921

Max Act: 0.6794. Min Act: -0.0000

Data Index: 532651 (C4 (Web Text))

Max Activating Token Index: 788