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

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

Neuron 188 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.3460. Min Act: -0.0000

Data Index: 1547987 (Python Code)

Max Activating Token Index: 75

Text #1

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.3559. Min Act: -0.0000

Data Index: 1046612 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.3296. Min Act: -0.0000

Data Index: 717433 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.3104. Min Act: -0.0000

Data Index: 1530389 (Python Code)

Max Activating Token Index: 632

Text #4

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.3123. Min Act: -0.0000

Data Index: 672759 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1013236 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2763. Min Act: -0.0000

Data Index: 1192776 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2919. Min Act: -0.0000

Data Index: 395434 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2901. Min Act: -0.0000

Data Index: 188926 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2777. Min Act: -0.0000

Data Index: 1305590 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2666. Min Act: -0.0000

Data Index: 19168 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2786. Min Act: -0.0000

Data Index: 793909 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2926. Min Act: -0.0000

Data Index: 1430676 (Python Code)

Max Activating Token Index: 250

Text #13

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2779. Min Act: -0.0000

Data Index: 767080 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2900. Min Act: -0.0000

Data Index: 1457750 (Python Code)

Max Activating Token Index: 728

Text #15

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2808. Min Act: -0.0000

Data Index: 728036 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2514. Min Act: -0.0000

Data Index: 1175094 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2692. Min Act: -0.0000

Data Index: 1391489 (Python Code)

Max Activating Token Index: 96

Text #18

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2649. Min Act: -0.0000

Data Index: 811290 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.3559. Min Range: -0.3559

Max Act: 0.2527. Min Act: -0.0000

Data Index: 1431113 (Python Code)

Max Activating Token Index: 296