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

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

Neuron 3239 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.9504. Min Act: -0.0001

Data Index: 1435549 (Python Code)

Max Activating Token Index: 539

Text #1

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.8140. Min Act: -0.0001

Data Index: 1076178 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.9064. Min Act: -0.0001

Data Index: 1564862 (Python Code)

Max Activating Token Index: 920

Text #3

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.8014. Min Act: -0.0001

Data Index: 532055 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.9763. Min Act: -0.0001

Data Index: 1648949 (Python Code)

Max Activating Token Index: 74

Text #5

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.9383. Min Act: -0.0001

Data Index: 456938 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7109. Min Act: -0.0001

Data Index: 1554602 (Python Code)

Max Activating Token Index: 31

Text #7

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7174. Min Act: -0.0001

Data Index: 1479467 (Python Code)

Max Activating Token Index: 619

Text #8

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7326. Min Act: -0.0001

Data Index: 1618815 (Python Code)

Max Activating Token Index: 897

Text #9

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7223. Min Act: -0.0001

Data Index: 1389718 (Python Code)

Max Activating Token Index: 22

Text #10

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.6863. Min Act: -0.0001

Data Index: 1421882 (Python Code)

Max Activating Token Index: 956

Text #11

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7388. Min Act: -0.0001

Data Index: 242154 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7641. Min Act: -0.0001

Data Index: 1654180 (Python Code)

Max Activating Token Index: 1001

Text #13

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.6927. Min Act: -0.0001

Data Index: 991974 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7326. Min Act: -0.0001

Data Index: 1441952 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7279. Min Act: -0.0001

Data Index: 892986 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7044. Min Act: -0.0001

Data Index: 986238 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7377. Min Act: -0.0001

Data Index: 900728 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.8142. Min Act: -0.0001

Data Index: 1595477 (Python Code)

Max Activating Token Index: 48

Text #19

Max Range: 0.9763. Min Range: -0.9763

Max Act: 0.7329. Min Act: -0.0001

Data Index: 415991 (C4 (Web Text))

Max Activating Token Index: 811