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

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

Neuron 2767 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: 0.5018. Min Range: -0.5018

Max Act: 0.5018. Min Act: -0.0000

Data Index: 36895 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1260731 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4390. Min Act: 0.0000

Data Index: 926180 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4531. Min Act: -0.0000

Data Index: 1315563 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4437. Min Act: 0.0000

Data Index: 606426 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1242386 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4539. Min Act: -0.0000

Data Index: 544194 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4321. Min Act: -0.0000

Data Index: 444277 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4705. Min Act: -0.0000

Data Index: 1206933 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4392. Min Act: 0.0000

Data Index: 873018 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3968. Min Act: 0.0000

Data Index: 1152220 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4398. Min Act: 0.0001

Data Index: 315510 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4198. Min Act: -0.0000

Data Index: 759741 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4136. Min Act: 0.0000

Data Index: 1180833 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3917. Min Act: -0.0000

Data Index: 781218 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3844. Min Act: -0.0000

Data Index: 570374 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3842. Min Act: -0.0000

Data Index: 1078223 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3963. Min Act: -0.0000

Data Index: 982701 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3776. Min Act: -0.0000

Data Index: 680390 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3889. Min Act: -0.0000

Data Index: 322324 (C4 (Web Text))

Max Activating Token Index: 597