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

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

Neuron 4842 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: 1.8928. Min Range: -1.8928

Max Act: 1.7005. Min Act: -0.0000

Data Index: 373939 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 1.8928. Min Range: -1.8928

Max Act: 1.8928. Min Act: -0.0000

Data Index: 1129878 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 1.8928. Min Range: -1.8928

Max Act: 1.3179. Min Act: -0.0000

Data Index: 263065 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 1.8928. Min Range: -1.8928

Max Act: 1.3133. Min Act: -0.0000

Data Index: 308271 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 1.8928. Min Range: -1.8928

Max Act: 1.2318. Min Act: 0.0000

Data Index: 318528 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 1.8928. Min Range: -1.8928

Max Act: 1.2072. Min Act: -0.0000

Data Index: 125397 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 1.8928. Min Range: -1.8928

Max Act: 1.2042. Min Act: -0.0000

Data Index: 24210 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 1.8928. Min Range: -1.8928

Max Act: 1.1632. Min Act: -0.0000

Data Index: 524128 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 1.8928. Min Range: -1.8928

Max Act: 1.1493. Min Act: -0.0000

Data Index: 924095 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 1.8928. Min Range: -1.8928

Max Act: 1.1217. Min Act: -0.0000

Data Index: 1236699 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 1.8928. Min Range: -1.8928

Max Act: 1.0268. Min Act: -0.0000

Data Index: 1333952 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 1.8928. Min Range: -1.8928

Max Act: 1.1762. Min Act: -0.0000

Data Index: 651937 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 1.8928. Min Range: -1.8928

Max Act: 1.0288. Min Act: -0.0000

Data Index: 23421 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 1.8928. Min Range: -1.8928

Max Act: 1.1452. Min Act: -0.0000

Data Index: 1173762 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 1.8928. Min Range: -1.8928

Max Act: 1.0767. Min Act: -0.0000

Data Index: 1054463 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 1.8928. Min Range: -1.8928

Max Act: 1.0744. Min Act: -0.0000

Data Index: 1131431 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 1.8928. Min Range: -1.8928

Max Act: 1.0032. Min Act: -0.0000

Data Index: 940352 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 1.8928. Min Range: -1.8928

Max Act: 1.0060. Min Act: -0.0000

Data Index: 555179 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 1.8928. Min Range: -1.8928

Max Act: 1.0139. Min Act: -0.0000

Data Index: 1206374 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 1.8928. Min Range: -1.8928

Max Act: 1.0095. Min Act: -0.0000

Data Index: 18569 (C4 (Web Text))

Max Activating Token Index: 910