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

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

Neuron 2433 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.7817. Min Act: -0.0000

Data Index: 816070 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.6728. Min Act: -0.0000

Data Index: 1489316 (Python Code)

Max Activating Token Index: 149

Text #2

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.6425. Min Act: -0.0000

Data Index: 1015820 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5934. Min Act: -0.0000

Data Index: 809435 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5955. Min Act: -0.0000

Data Index: 996437 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5967. Min Act: -0.0000

Data Index: 1333838 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5758. Min Act: -0.0000

Data Index: 36767 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1019423 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5219. Min Act: -0.0000

Data Index: 598957 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5305. Min Act: -0.0000

Data Index: 606388 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5583. Min Act: -0.0000

Data Index: 309032 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5156. Min Act: -0.0000

Data Index: 49589 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1145780 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5469. Min Act: -0.0000

Data Index: 240196 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.4955. Min Act: -0.0000

Data Index: 467272 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5060. Min Act: -0.0000

Data Index: 1569818 (Python Code)

Max Activating Token Index: 57

Text #16

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5397. Min Act: -0.0000

Data Index: 380702 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5189. Min Act: -0.0000

Data Index: 290936 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1369451 (Python Code)

Max Activating Token Index: 750

Text #19

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5040. Min Act: -0.0000

Data Index: 412539 (C4 (Web Text))

Max Activating Token Index: 79