Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3102 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3780. Min Range: -1.3780

Max Act: 1.3780. Min Act: -0.0000

Data Index: 1070473 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 1.3780. Min Range: -1.3780

Max Act: 1.0206. Min Act: -0.0001

Data Index: 1348235 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.9822. Min Act: -0.0000

Data Index: 452006 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.9202. Min Act: -0.0000

Data Index: 182997 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.9625. Min Act: -0.0000

Data Index: 163520 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.9258. Min Act: -0.0001

Data Index: 715439 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.9486. Min Act: -0.0000

Data Index: 136785 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.9391. Min Act: -0.0000

Data Index: 661511 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.8491. Min Act: -0.0000

Data Index: 1302291 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.8590. Min Act: -0.0001

Data Index: 178762 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.9164. Min Act: -0.0000

Data Index: 818872 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.8779. Min Act: -0.0000

Data Index: 1301153 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.8317. Min Act: -0.0000

Data Index: 183620 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.8249. Min Act: -0.0000

Data Index: 481468 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.7521. Min Act: -0.0000

Data Index: 1168999 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.8171. Min Act: -0.0000

Data Index: 449138 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.8461. Min Act: -0.0001

Data Index: 1118896 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.8174. Min Act: -0.0001

Data Index: 78178 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.8063. Min Act: -0.0000

Data Index: 898114 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 1.3780. Min Range: -1.3780

Max Act: 0.8051. Min Act: -0.0000

Data Index: 586799 (C4 (Web Text))

Max Activating Token Index: 217