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

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

Neuron 617 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.3103. Min Act: -0.0001

Data Index: 14688 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.2456. Min Act: -0.0000

Data Index: 171435 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.1811. Min Act: -0.0001

Data Index: 1426874 (Python Code)

Max Activating Token Index: 697

Text #3

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.1870. Min Act: -0.0000

Data Index: 1394820 (Python Code)

Max Activating Token Index: 298

Text #4

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.1952. Min Act: -0.0000

Data Index: 885992 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.1819. Min Act: -0.0001

Data Index: 1106433 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1017444 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.1682. Min Act: -0.0000

Data Index: 692128 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.1703. Min Act: -0.0000

Data Index: 279250 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.1584. Min Act: -0.0000

Data Index: 1026791 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.1686. Min Act: -0.0001

Data Index: 1065401 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.1574. Min Act: -0.0000

Data Index: 312945 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.1560. Min Act: -0.0000

Data Index: 749442 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1337999 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.1553. Min Act: -0.0000

Data Index: 1279607 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.1514. Min Act: -0.0000

Data Index: 1149913 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.1451. Min Act: -0.0000

Data Index: 872273 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.1482. Min Act: -0.0000

Data Index: 521163 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.1431. Min Act: -0.0001

Data Index: 247404 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.3103. Min Range: -0.3103

Max Act: 0.1457. Min Act: -0.0000

Data Index: 726554 (C4 (Web Text))

Max Activating Token Index: 668