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

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

Neuron 2997 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6603. Min Act: -0.0000

Data Index: 1511939 (Python Code)

Max Activating Token Index: 393

Text #1

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6729. Min Act: -0.0000

Data Index: 607123 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1499103 (Python Code)

Max Activating Token Index: 767

Text #3

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6451. Min Act: -0.0000

Data Index: 1494916 (Python Code)

Max Activating Token Index: 603

Text #4

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6051. Min Act: -0.0000

Data Index: 1474450 (Python Code)

Max Activating Token Index: 204

Text #5

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1493109 (Python Code)

Max Activating Token Index: 473

Text #6

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5654. Min Act: -0.0000

Data Index: 814868 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5105. Min Act: -0.0000

Data Index: 630744 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5328. Min Act: -0.0000

Data Index: 913125 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5464. Min Act: -0.0000

Data Index: 248329 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5667. Min Act: -0.0000

Data Index: 756056 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5119. Min Act: -0.0000

Data Index: 1238164 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5525. Min Act: -0.0000

Data Index: 902051 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5013. Min Act: -0.0000

Data Index: 1407738 (Python Code)

Max Activating Token Index: 359

Text #14

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.4942. Min Act: -0.0000

Data Index: 1097983 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.4509. Min Act: -0.0000

Data Index: 325818 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1093954 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5221. Min Act: -0.0000

Data Index: 992873 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1113355 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.7630. Min Range: -0.7630

Max Act: 0.5112. Min Act: -0.0000

Data Index: 487441 (C4 (Web Text))

Max Activating Token Index: 997