Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1771 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.7681. Min Act: -0.0000

Data Index: 1255948 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.5322. Min Act: -0.0000

Data Index: 166426 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.5084. Min Act: -0.0000

Data Index: 1154433 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.4161. Min Act: -0.0000

Data Index: 770257 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.3690. Min Act: -0.0000

Data Index: 576627 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.3867. Min Act: -0.0000

Data Index: 361613 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.3138. Min Act: -0.0000

Data Index: 820277 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.2519. Min Act: -0.0000

Data Index: 821391 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.2624. Min Act: -0.0000

Data Index: 903921 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.2017. Min Act: -0.0000

Data Index: 1016165 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.1546. Min Act: -0.0000

Data Index: 477416 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.1834. Min Act: -0.0000

Data Index: 625077 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.2018. Min Act: -0.0000

Data Index: 913330 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.1585. Min Act: -0.0000

Data Index: 478947 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.1419. Min Act: -0.0000

Data Index: 194793 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.1005. Min Act: -0.0000

Data Index: 417899 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.0722. Min Act: -0.0000

Data Index: 862641 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.1066. Min Act: -0.0000

Data Index: 895616 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.1316. Min Act: -0.0000

Data Index: 1065944 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 1.7681. Min Range: -1.7681

Max Act: 1.0932. Min Act: -0.0000

Data Index: 886528 (C4 (Web Text))

Max Activating Token Index: 33