Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1596 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3767. Min Range: -1.3767

Max Act: 1.3767. Min Act: -0.0001

Data Index: 33870 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 1.3767. Min Range: -1.3767

Max Act: 1.3105. Min Act: -0.0001

Data Index: 649780 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 1.3767. Min Range: -1.3767

Max Act: 1.2420. Min Act: -0.0000

Data Index: 244643 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 1.3767. Min Range: -1.3767

Max Act: 1.2443. Min Act: -0.0001

Data Index: 166509 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 1.3767. Min Range: -1.3767

Max Act: 1.3107. Min Act: -0.0000

Data Index: 567700 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 1.3767. Min Range: -1.3767

Max Act: 1.2217. Min Act: -0.0001

Data Index: 1151965 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 1.3767. Min Range: -1.3767

Max Act: 1.1661. Min Act: -0.0000

Data Index: 431315 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 1.3767. Min Range: -1.3767

Max Act: 1.2399. Min Act: -0.0000

Data Index: 646088 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 1.3767. Min Range: -1.3767

Max Act: 1.1565. Min Act: -0.0000

Data Index: 468367 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 1.3767. Min Range: -1.3767

Max Act: 1.1263. Min Act: -0.0000

Data Index: 950772 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 1.3767. Min Range: -1.3767

Max Act: 1.1488. Min Act: -0.0000

Data Index: 1257060 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 1.3767. Min Range: -1.3767

Max Act: 1.2409. Min Act: -0.0001

Data Index: 87775 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 1.3767. Min Range: -1.3767

Max Act: 1.1875. Min Act: -0.0001

Data Index: 402211 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 1.3767. Min Range: -1.3767

Max Act: 1.1603. Min Act: -0.0001

Data Index: 693830 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 1.3767. Min Range: -1.3767

Max Act: 1.0981. Min Act: -0.0001

Data Index: 269847 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 1.3767. Min Range: -1.3767

Max Act: 1.0836. Min Act: -0.0000

Data Index: 870783 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 1.3767. Min Range: -1.3767

Max Act: 1.2096. Min Act: -0.0000

Data Index: 16238 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 1.3767. Min Range: -1.3767

Max Act: 1.0402. Min Act: -0.0001

Data Index: 1090838 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 1.3767. Min Range: -1.3767

Max Act: 1.3046. Min Act: -0.0000

Data Index: 120180 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 1.3767. Min Range: -1.3767

Max Act: 1.1876. Min Act: -0.0001

Data Index: 42488 (C4 (Web Text))

Max Activating Token Index: 702