Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 116 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2819. Min Act: -0.0001

Data Index: 999738 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2542. Min Act: -0.0001

Data Index: 744992 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2382. Min Act: -0.0001

Data Index: 192466 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2454. Min Act: -0.0001

Data Index: 1235211 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2368. Min Act: -0.0001

Data Index: 109613 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2279. Min Act: -0.0001

Data Index: 191486 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2231. Min Act: -0.0001

Data Index: 1222605 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2112. Min Act: -0.0001

Data Index: 205225 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2090. Min Act: -0.0001

Data Index: 1105542 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1963. Min Act: -0.0001

Data Index: 1235931 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1782. Min Act: -0.0001

Data Index: 602840 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1923. Min Act: -0.0001

Data Index: 871272 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1980. Min Act: -0.0001

Data Index: 929287 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1953. Min Act: -0.0001

Data Index: 1259204 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2035. Min Act: -0.0001

Data Index: 419743 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1946. Min Act: -0.0001

Data Index: 710704 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1870. Min Act: -0.0001

Data Index: 825122 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2004. Min Act: -0.0001

Data Index: 561600 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1893. Min Act: -0.0001

Data Index: 1064852 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1620. Min Act: -0.0001

Data Index: 329399 (C4 (Web Text))

Max Activating Token Index: 342