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

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

Neuron 22 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: 1.3978. Min Range: -1.3978

Max Act: 1.3978. Min Act: -0.0000

Data Index: 687321 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.3182. Min Act: -0.0000

Data Index: 511202 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.2658. Min Act: -0.0000

Data Index: 664599 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.2394. Min Act: -0.0000

Data Index: 546904 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0832. Min Act: -0.0000

Data Index: 863388 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0483. Min Act: -0.0000

Data Index: 1278882 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0955. Min Act: -0.0000

Data Index: 801273 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0135. Min Act: -0.0000

Data Index: 832061 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0242. Min Act: -0.0000

Data Index: 1480108 (Python Code)

Max Activating Token Index: 762

Text #9

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0456. Min Act: -0.0000

Data Index: 429939 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0027. Min Act: -0.0000

Data Index: 517724 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 1.3978. Min Range: -1.3978

Max Act: 0.7852. Min Act: -0.0000

Data Index: 763776 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 1.3978. Min Range: -1.3978

Max Act: 0.9204. Min Act: -0.0000

Data Index: 777416 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 1.3978. Min Range: -1.3978

Max Act: 0.9652. Min Act: -0.0000

Data Index: 1586244 (Python Code)

Max Activating Token Index: 645

Text #14

Max Range: 1.3978. Min Range: -1.3978

Max Act: 0.8732. Min Act: -0.0000

Data Index: 560644 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 1.3978. Min Range: -1.3978

Max Act: 0.8865. Min Act: -0.0000

Data Index: 501109 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 1.3978. Min Range: -1.3978

Max Act: 0.9099. Min Act: -0.0000

Data Index: 120685 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 1.3978. Min Range: -1.3978

Max Act: 0.9370. Min Act: -0.0000

Data Index: 980130 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 1.3978. Min Range: -1.3978

Max Act: 0.8165. Min Act: -0.0000

Data Index: 638342 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 1.3978. Min Range: -1.3978

Max Act: 0.8372. Min Act: -0.0000

Data Index: 812862 (C4 (Web Text))

Max Activating Token Index: 425