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

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

Neuron 1328 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.6268. Min Act: -0.0001

Data Index: 430947 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5112. Min Act: -0.0001

Data Index: 416915 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4879. Min Act: -0.0001

Data Index: 1110126 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4700. Min Act: -0.0001

Data Index: 358644 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4680. Min Act: -0.0001

Data Index: 176167 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4848. Min Act: -0.0001

Data Index: 706567 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4630. Min Act: -0.0001

Data Index: 91942 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4755. Min Act: -0.0001

Data Index: 1007460 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4609. Min Act: -0.0000

Data Index: 314895 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4358. Min Act: -0.0001

Data Index: 815486 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4504. Min Act: -0.0001

Data Index: 61756 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4596. Min Act: -0.0001

Data Index: 704860 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4698. Min Act: -0.0000

Data Index: 1260500 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4229. Min Act: -0.0000

Data Index: 1262457 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4373. Min Act: -0.0001

Data Index: 64577 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4490. Min Act: -0.0001

Data Index: 177436 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4474. Min Act: -0.0001

Data Index: 1091200 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4467. Min Act: -0.0001

Data Index: 1270098 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1008505 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4373. Min Act: -0.0000

Data Index: 1226431 (C4 (Web Text))

Max Activating Token Index: 978