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

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

Neuron 2921 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: 1.6098. Min Range: -1.6098

Max Act: 1.5374. Min Act: -0.0000

Data Index: 328169 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 1.6098. Min Range: -1.6098

Max Act: 1.6098. Min Act: -0.0000

Data Index: 461285 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 1.6098. Min Range: -1.6098

Max Act: 1.5824. Min Act: -0.0000

Data Index: 27704 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 1.6098. Min Range: -1.6098

Max Act: 1.4271. Min Act: -0.0000

Data Index: 530402 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 1.6098. Min Range: -1.6098

Max Act: 1.4423. Min Act: -0.0000

Data Index: 772974 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 1.6098. Min Range: -1.6098

Max Act: 1.2682. Min Act: -0.0000

Data Index: 1186133 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 1.6098. Min Range: -1.6098

Max Act: 1.1256. Min Act: -0.0000

Data Index: 172641 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 1.6098. Min Range: -1.6098

Max Act: 1.0535. Min Act: -0.0000

Data Index: 699126 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 1.6098. Min Range: -1.6098

Max Act: 1.3130. Min Act: -0.0000

Data Index: 347226 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 1.6098. Min Range: -1.6098

Max Act: 1.0982. Min Act: -0.0000

Data Index: 776922 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 1.6098. Min Range: -1.6098

Max Act: 1.0491. Min Act: -0.0000

Data Index: 1282465 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 1.6098. Min Range: -1.6098

Max Act: 1.1073. Min Act: -0.0000

Data Index: 559937 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 1.6098. Min Range: -1.6098

Max Act: 1.0491. Min Act: -0.0000

Data Index: 754049 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 1.6098. Min Range: -1.6098

Max Act: 1.0343. Min Act: -0.0000

Data Index: 1179904 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 1.6098. Min Range: -1.6098

Max Act: 1.0868. Min Act: -0.0000

Data Index: 1355320 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 1.6098. Min Range: -1.6098

Max Act: 1.0905. Min Act: -0.0000

Data Index: 710912 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 1.6098. Min Range: -1.6098

Max Act: 1.0939. Min Act: -0.0000

Data Index: 342228 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 1.6098. Min Range: -1.6098

Max Act: 1.0866. Min Act: -0.0000

Data Index: 482278 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 1.6098. Min Range: -1.6098

Max Act: 1.1360. Min Act: -0.0000

Data Index: 69932 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 1.6098. Min Range: -1.6098

Max Act: 1.0615. Min Act: -0.0000

Data Index: 526335 (C4 (Web Text))

Max Activating Token Index: 98