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

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

Neuron 3071 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3253. Min Range: -7.3253

Max Act: 7.2340. Min Act: -0.0000

Data Index: 517170 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 7.3253. Min Range: -7.3253

Max Act: 7.3253. Min Act: -0.0000

Data Index: 658693 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 7.3253. Min Range: -7.3253

Max Act: 6.8749. Min Act: -0.0000

Data Index: 273683 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 7.3253. Min Range: -7.3253

Max Act: 6.4224. Min Act: -0.0000

Data Index: 1592004 (Python Code)

Max Activating Token Index: 1017

Text #4

Max Range: 7.3253. Min Range: -7.3253

Max Act: 6.9050. Min Act: -0.0000

Data Index: 1175690 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 7.3253. Min Range: -7.3253

Max Act: 6.5937. Min Act: -0.0000

Data Index: 197032 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 7.3253. Min Range: -7.3253

Max Act: 6.4238. Min Act: -0.0000

Data Index: 328095 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 7.3253. Min Range: -7.3253

Max Act: 7.1001. Min Act: -0.0000

Data Index: 671446 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 7.3253. Min Range: -7.3253

Max Act: 6.3677. Min Act: -0.0000

Data Index: 143562 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 7.3253. Min Range: -7.3253

Max Act: 6.5348. Min Act: -0.0000

Data Index: 404241 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 7.3253. Min Range: -7.3253

Max Act: 6.3298. Min Act: -0.0000

Data Index: 390238 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 7.3253. Min Range: -7.3253

Max Act: 6.6500. Min Act: -0.0000

Data Index: 1537865 (Python Code)

Max Activating Token Index: 56

Text #12

Max Range: 7.3253. Min Range: -7.3253

Max Act: 6.4595. Min Act: -0.0000

Data Index: 1587800 (Python Code)

Max Activating Token Index: 511

Text #13

Max Range: 7.3253. Min Range: -7.3253

Max Act: 6.3625. Min Act: -0.0000

Data Index: 530781 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 7.3253. Min Range: -7.3253

Max Act: 6.3556. Min Act: -0.0000

Data Index: 220963 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 7.3253. Min Range: -7.3253

Max Act: 6.2868. Min Act: -0.0000

Data Index: 1079151 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 7.3253. Min Range: -7.3253

Max Act: 5.8453. Min Act: -0.0000

Data Index: 349105 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 7.3253. Min Range: -7.3253

Max Act: 6.1897. Min Act: -0.0000

Data Index: 930600 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 7.3253. Min Range: -7.3253

Max Act: 5.8579. Min Act: -0.0000

Data Index: 927933 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 7.3253. Min Range: -7.3253

Max Act: 6.1911. Min Act: -0.0000

Data Index: 841052 (C4 (Web Text))

Max Activating Token Index: 930