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

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

Neuron 3320 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1884. Min Range: -1.1884

Max Act: 1.1884. Min Act: -0.0000

Data Index: 1163708 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 1.1884. Min Range: -1.1884

Max Act: 1.1870. Min Act: -0.0000

Data Index: 528151 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 1.1884. Min Range: -1.1884

Max Act: 1.1423. Min Act: -0.0000

Data Index: 451442 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 1.1884. Min Range: -1.1884

Max Act: 1.0988. Min Act: -0.0000

Data Index: 767228 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 1.1884. Min Range: -1.1884

Max Act: 1.0586. Min Act: -0.0000

Data Index: 817436 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 1.1884. Min Range: -1.1884

Max Act: 1.0292. Min Act: -0.0000

Data Index: 175008 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.9918. Min Act: -0.0000

Data Index: 747927 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.9983. Min Act: -0.0000

Data Index: 946844 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 1.1884. Min Range: -1.1884

Max Act: 1.0285. Min Act: -0.0000

Data Index: 1129900 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 1.1884. Min Range: -1.1884

Max Act: 1.0032. Min Act: -0.0000

Data Index: 893622 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.9923. Min Act: -0.0000

Data Index: 779777 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.9196. Min Act: -0.0000

Data Index: 1234991 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.9131. Min Act: -0.0000

Data Index: 2050 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.8764. Min Act: -0.0000

Data Index: 130095 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.8975. Min Act: -0.0000

Data Index: 395790 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.9268. Min Act: -0.0000

Data Index: 475851 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.9001. Min Act: -0.0000

Data Index: 502777 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.8871. Min Act: -0.0000

Data Index: 671361 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.9132. Min Act: -0.0000

Data Index: 897709 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 1.1884. Min Range: -1.1884

Max Act: 0.9357. Min Act: -0.0000

Data Index: 1170938 (C4 (Web Text))

Max Activating Token Index: 945