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

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

Neuron 2568 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: 3.0326. Min Range: -3.0326

Max Act: 3.0176. Min Act: -0.0000

Data Index: 1306865 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 3.0326. Min Range: -3.0326

Max Act: 2.9584. Min Act: -0.0000

Data Index: 854470 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 3.0326. Min Range: -3.0326

Max Act: 2.8654. Min Act: -0.0000

Data Index: 102985 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 3.0326. Min Range: -3.0326

Max Act: 3.0326. Min Act: -0.0000

Data Index: 868308 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 3.0326. Min Range: -3.0326

Max Act: 2.9430. Min Act: -0.0000

Data Index: 790688 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 3.0326. Min Range: -3.0326

Max Act: 2.7842. Min Act: -0.0000

Data Index: 1185445 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 3.0326. Min Range: -3.0326

Max Act: 2.8552. Min Act: -0.0000

Data Index: 678436 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 3.0326. Min Range: -3.0326

Max Act: 2.7329. Min Act: -0.0000

Data Index: 800327 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 3.0326. Min Range: -3.0326

Max Act: 2.5708. Min Act: -0.0000

Data Index: 363335 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 3.0326. Min Range: -3.0326

Max Act: 2.8330. Min Act: -0.0000

Data Index: 723620 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 3.0326. Min Range: -3.0326

Max Act: 2.6021. Min Act: -0.0000

Data Index: 1164128 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 3.0326. Min Range: -3.0326

Max Act: 2.4709. Min Act: -0.0000

Data Index: 60026 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 3.0326. Min Range: -3.0326

Max Act: 2.4642. Min Act: -0.0000

Data Index: 1184712 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 3.0326. Min Range: -3.0326

Max Act: 2.4261. Min Act: -0.0000

Data Index: 138062 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 3.0326. Min Range: -3.0326

Max Act: 2.5318. Min Act: -0.0000

Data Index: 876394 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 3.0326. Min Range: -3.0326

Max Act: 2.3212. Min Act: -0.0000

Data Index: 332880 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 3.0326. Min Range: -3.0326

Max Act: 2.4429. Min Act: -0.0000

Data Index: 1012413 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 3.0326. Min Range: -3.0326

Max Act: 2.5541. Min Act: -0.0000

Data Index: 347744 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 3.0326. Min Range: -3.0326

Max Act: 2.6292. Min Act: -0.0000

Data Index: 204176 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 3.0326. Min Range: -3.0326

Max Act: 2.3031. Min Act: -0.0000

Data Index: 924037 (C4 (Web Text))

Max Activating Token Index: 165