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

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

Neuron 5709 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1397. Min Range: -4.1397

Max Act: 4.0336. Min Act: -0.0000

Data Index: 1024368 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 4.1397. Min Range: -4.1397

Max Act: 4.0566. Min Act: -0.0000

Data Index: 1203653 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 4.1397. Min Range: -4.1397

Max Act: 3.9820. Min Act: -0.0001

Data Index: 529359 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 4.1397. Min Range: -4.1397

Max Act: 3.6163. Min Act: -0.0001

Data Index: 492094 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 4.1397. Min Range: -4.1397

Max Act: 3.7391. Min Act: -0.0001

Data Index: 493741 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 4.1397. Min Range: -4.1397

Max Act: 4.0385. Min Act: -0.0001

Data Index: 39607 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 4.1397. Min Range: -4.1397

Max Act: 4.1397. Min Act: -0.0001

Data Index: 668364 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 4.1397. Min Range: -4.1397

Max Act: 3.8705. Min Act: -0.0001

Data Index: 422646 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 4.1397. Min Range: -4.1397

Max Act: 3.6042. Min Act: -0.0001

Data Index: 1310851 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 4.1397. Min Range: -4.1397

Max Act: 4.0196. Min Act: -0.0000

Data Index: 270480 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 4.1397. Min Range: -4.1397

Max Act: 3.2920. Min Act: -0.0001

Data Index: 1141816 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 4.1397. Min Range: -4.1397

Max Act: 3.0706. Min Act: -0.0001

Data Index: 221230 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 4.1397. Min Range: -4.1397

Max Act: 3.0543. Min Act: -0.0000

Data Index: 754253 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 4.1397. Min Range: -4.1397

Max Act: 3.0174. Min Act: -0.0001

Data Index: 438846 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 4.1397. Min Range: -4.1397

Max Act: 3.0867. Min Act: -0.0001

Data Index: 177233 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 4.1397. Min Range: -4.1397

Max Act: 3.4058. Min Act: -0.0001

Data Index: 858115 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 4.1397. Min Range: -4.1397

Max Act: 2.8887. Min Act: -0.0001

Data Index: 559377 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 4.1397. Min Range: -4.1397

Max Act: 3.0432. Min Act: -0.0000

Data Index: 1344372 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 4.1397. Min Range: -4.1397

Max Act: 2.9326. Min Act: -0.0001

Data Index: 491264 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 4.1397. Min Range: -4.1397

Max Act: 3.4260. Min Act: -0.0001

Data Index: 802661 (C4 (Web Text))

Max Activating Token Index: 373