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

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

Neuron 18 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.3884. Min Act: -0.0000

Data Index: 702346 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.0599. Min Act: -0.0000

Data Index: 1125466 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 3.3884. Min Range: -3.3884

Max Act: 2.9211. Min Act: -0.0000

Data Index: 728252 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 3.3884. Min Range: -3.3884

Max Act: 2.9119. Min Act: -0.0000

Data Index: 1214541 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 3.3884. Min Range: -3.3884

Max Act: 2.7493. Min Act: -0.0000

Data Index: 354464 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.0231. Min Act: -0.0000

Data Index: 494308 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 3.3884. Min Range: -3.3884

Max Act: 2.8846. Min Act: -0.0000

Data Index: 1150283 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 3.3884. Min Range: -3.3884

Max Act: 2.3969. Min Act: -0.0000

Data Index: 336341 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 3.3884. Min Range: -3.3884

Max Act: 2.6384. Min Act: -0.0000

Data Index: 478724 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 3.3884. Min Range: -3.3884

Max Act: 2.8255. Min Act: -0.0000

Data Index: 300030 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 3.3884. Min Range: -3.3884

Max Act: 2.4861. Min Act: -0.0000

Data Index: 1041841 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 3.3884. Min Range: -3.3884

Max Act: 2.6126. Min Act: -0.0000

Data Index: 1007622 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 3.3884. Min Range: -3.3884

Max Act: 2.3989. Min Act: -0.0000

Data Index: 1066486 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 3.3884. Min Range: -3.3884

Max Act: 2.3673. Min Act: -0.0000

Data Index: 726068 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 3.3884. Min Range: -3.3884

Max Act: 2.4809. Min Act: -0.0000

Data Index: 751792 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 3.3884. Min Range: -3.3884

Max Act: 2.2543. Min Act: -0.0000

Data Index: 197444 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 3.3884. Min Range: -3.3884

Max Act: 2.1871. Min Act: -0.0000

Data Index: 1191117 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 3.3884. Min Range: -3.3884

Max Act: 2.1453. Min Act: -0.0000

Data Index: 760557 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 3.3884. Min Range: -3.3884

Max Act: 2.1557. Min Act: -0.0000

Data Index: 1167961 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 3.3884. Min Range: -3.3884

Max Act: 2.3884. Min Act: -0.0000

Data Index: 737297 (C4 (Web Text))

Max Activating Token Index: 56