Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3969 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2445. Min Range: -3.2445

Max Act: 3.2445. Min Act: -0.0000

Data Index: 1108600 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 3.2445. Min Range: -3.2445

Max Act: 3.1873. Min Act: -0.0000

Data Index: 464606 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 3.2445. Min Range: -3.2445

Max Act: 2.6585. Min Act: -0.0000

Data Index: 335722 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 3.2445. Min Range: -3.2445

Max Act: 2.5909. Min Act: -0.0000

Data Index: 858287 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 3.2445. Min Range: -3.2445

Max Act: 2.6325. Min Act: -0.0000

Data Index: 913632 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 3.2445. Min Range: -3.2445

Max Act: 2.8225. Min Act: -0.0000

Data Index: 826178 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 3.2445. Min Range: -3.2445

Max Act: 2.4479. Min Act: -0.0000

Data Index: 690483 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 3.2445. Min Range: -3.2445

Max Act: 2.4290. Min Act: -0.0000

Data Index: 470462 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 3.2445. Min Range: -3.2445

Max Act: 2.4113. Min Act: -0.0000

Data Index: 1038789 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 3.2445. Min Range: -3.2445

Max Act: 2.4007. Min Act: -0.0000

Data Index: 186075 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 3.2445. Min Range: -3.2445

Max Act: 2.3845. Min Act: -0.0000

Data Index: 139991 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 3.2445. Min Range: -3.2445

Max Act: 2.5066. Min Act: -0.0000

Data Index: 1197181 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 3.2445. Min Range: -3.2445

Max Act: 2.2010. Min Act: -0.0000

Data Index: 141657 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 3.2445. Min Range: -3.2445

Max Act: 2.2659. Min Act: -0.0000

Data Index: 435923 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 3.2445. Min Range: -3.2445

Max Act: 2.0020. Min Act: -0.0000

Data Index: 434933 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 3.2445. Min Range: -3.2445

Max Act: 2.0862. Min Act: -0.0000

Data Index: 1292815 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 3.2445. Min Range: -3.2445

Max Act: 1.8549. Min Act: -0.0000

Data Index: 361274 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 3.2445. Min Range: -3.2445

Max Act: 1.8443. Min Act: -0.0000

Data Index: 31673 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 3.2445. Min Range: -3.2445

Max Act: 1.9483. Min Act: -0.0000

Data Index: 919446 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 3.2445. Min Range: -3.2445

Max Act: 1.9307. Min Act: -0.0000

Data Index: 215870 (C4 (Web Text))

Max Activating Token Index: 810