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

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

Neuron 2754 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3419. Min Range: -4.3419

Max Act: 4.3419. Min Act: -0.0000

Data Index: 1186040 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 4.3419. Min Range: -4.3419

Max Act: 3.7978. Min Act: -0.0000

Data Index: 909690 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 4.3419. Min Range: -4.3419

Max Act: 3.6861. Min Act: -0.0000

Data Index: 255808 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 4.3419. Min Range: -4.3419

Max Act: 3.3268. Min Act: -0.0001

Data Index: 339473 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 4.3419. Min Range: -4.3419

Max Act: 3.6305. Min Act: -0.0001

Data Index: 1032018 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 4.3419. Min Range: -4.3419

Max Act: 3.0717. Min Act: -0.0000

Data Index: 79246 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 4.3419. Min Range: -4.3419

Max Act: 3.3233. Min Act: -0.0001

Data Index: 432348 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 4.3419. Min Range: -4.3419

Max Act: 2.8343. Min Act: -0.0001

Data Index: 322200 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 4.3419. Min Range: -4.3419

Max Act: 2.7921. Min Act: -0.0001

Data Index: 1025236 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 4.3419. Min Range: -4.3419

Max Act: 3.1021. Min Act: -0.0001

Data Index: 734205 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 4.3419. Min Range: -4.3419

Max Act: 2.8468. Min Act: -0.0001

Data Index: 940964 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 4.3419. Min Range: -4.3419

Max Act: 2.6698. Min Act: -0.0001

Data Index: 1149218 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 4.3419. Min Range: -4.3419

Max Act: 3.1937. Min Act: -0.0001

Data Index: 457352 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 4.3419. Min Range: -4.3419

Max Act: 2.4845. Min Act: -0.0000

Data Index: 724915 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 4.3419. Min Range: -4.3419

Max Act: 2.7380. Min Act: -0.0001

Data Index: 382943 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 4.3419. Min Range: -4.3419

Max Act: 2.8145. Min Act: -0.0001

Data Index: 164027 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 4.3419. Min Range: -4.3419

Max Act: 2.6712. Min Act: -0.0000

Data Index: 1315920 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 4.3419. Min Range: -4.3419

Max Act: 2.6055. Min Act: -0.0001

Data Index: 1339542 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 4.3419. Min Range: -4.3419

Max Act: 2.1799. Min Act: -0.0000

Data Index: 1184712 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 4.3419. Min Range: -4.3419

Max Act: 2.3885. Min Act: -0.0000

Data Index: 210563 (C4 (Web Text))

Max Activating Token Index: 778