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

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

Neuron 3908 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3489. Min Range: -4.3489

Max Act: 4.3489. Min Act: -0.0000

Data Index: 476708 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 4.3489. Min Range: -4.3489

Max Act: 4.0347. Min Act: -0.0000

Data Index: 562739 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.8164. Min Act: -0.0000

Data Index: 876605 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.7861. Min Act: -0.0000

Data Index: 450948 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.7411. Min Act: -0.0000

Data Index: 901495 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.6660. Min Act: -0.0000

Data Index: 1040669 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.5590. Min Act: -0.0000

Data Index: 1179983 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.5551. Min Act: -0.0000

Data Index: 698012 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.3158. Min Act: -0.0000

Data Index: 1296315 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.5854. Min Act: -0.0000

Data Index: 325707 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.3802. Min Act: -0.0000

Data Index: 989041 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.1867. Min Act: -0.0000

Data Index: 352369 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.2955. Min Act: -0.0000

Data Index: 455060 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.2871. Min Act: -0.0000

Data Index: 801125 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.2174. Min Act: -0.0000

Data Index: 295496 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.1479. Min Act: -0.0000

Data Index: 583469 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.2607. Min Act: -0.0000

Data Index: 174083 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.2236. Min Act: -0.0000

Data Index: 591470 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.0474. Min Act: -0.0000

Data Index: 952255 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 4.3489. Min Range: -4.3489

Max Act: 3.3662. Min Act: -0.0000

Data Index: 1318846 (C4 (Web Text))

Max Activating Token Index: 968