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

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

Neuron 2020 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5292. Min Range: -3.5292

Max Act: 3.5292. Min Act: -0.0000

Data Index: 963092 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 3.5292. Min Range: -3.5292

Max Act: 3.1548. Min Act: -0.0000

Data Index: 198871 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 3.5292. Min Range: -3.5292

Max Act: 2.9127. Min Act: -0.0000

Data Index: 379286 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 3.5292. Min Range: -3.5292

Max Act: 3.1493. Min Act: -0.0000

Data Index: 378373 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 3.5292. Min Range: -3.5292

Max Act: 3.0415. Min Act: -0.0000

Data Index: 574846 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 3.5292. Min Range: -3.5292

Max Act: 2.9110. Min Act: -0.0000

Data Index: 140729 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 3.5292. Min Range: -3.5292

Max Act: 2.8391. Min Act: -0.0000

Data Index: 694961 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 3.5292. Min Range: -3.5292

Max Act: 2.7086. Min Act: -0.0000

Data Index: 671422 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 3.5292. Min Range: -3.5292

Max Act: 2.5283. Min Act: -0.0000

Data Index: 1050222 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 3.5292. Min Range: -3.5292

Max Act: 2.5183. Min Act: -0.0000

Data Index: 319229 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 3.5292. Min Range: -3.5292

Max Act: 2.6623. Min Act: -0.0000

Data Index: 136989 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 3.5292. Min Range: -3.5292

Max Act: 2.7619. Min Act: -0.0000

Data Index: 1004730 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 3.5292. Min Range: -3.5292

Max Act: 2.5893. Min Act: -0.0000

Data Index: 499756 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 3.5292. Min Range: -3.5292

Max Act: 2.7043. Min Act: -0.0000

Data Index: 275368 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 3.5292. Min Range: -3.5292

Max Act: 2.3553. Min Act: -0.0000

Data Index: 358778 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 3.5292. Min Range: -3.5292

Max Act: 2.6686. Min Act: -0.0000

Data Index: 1156428 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 3.5292. Min Range: -3.5292

Max Act: 2.5362. Min Act: -0.0000

Data Index: 548116 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 3.5292. Min Range: -3.5292

Max Act: 2.5235. Min Act: -0.0000

Data Index: 1168541 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 3.5292. Min Range: -3.5292

Max Act: 2.3721. Min Act: -0.0000

Data Index: 784961 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 3.5292. Min Range: -3.5292

Max Act: 2.4600. Min Act: -0.0000

Data Index: 639372 (C4 (Web Text))

Max Activating Token Index: 995