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

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

Neuron 1843 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.8937. Min Act: -0.0001

Data Index: 1369831 (Python Code)

Max Activating Token Index: 128

Text #1

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.8603. Min Act: -0.0001

Data Index: 1481928 (Python Code)

Max Activating Token Index: 807

Text #2

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.8830. Min Act: -0.0001

Data Index: 19986 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.8995. Min Act: -0.0001

Data Index: 1517982 (Python Code)

Max Activating Token Index: 727

Text #4

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.8544. Min Act: -0.0001

Data Index: 1425119 (Python Code)

Max Activating Token Index: 105

Text #5

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.8064. Min Act: -0.0001

Data Index: 1566284 (Python Code)

Max Activating Token Index: 752

Text #6

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.8252. Min Act: -0.0001

Data Index: 1497698 (Python Code)

Max Activating Token Index: 84

Text #7

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.7997. Min Act: -0.0001

Data Index: 1047941 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.8512. Min Act: -0.0001

Data Index: 879909 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.8750. Min Act: -0.0001

Data Index: 987060 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.8068. Min Act: -0.0001

Data Index: 1423908 (Python Code)

Max Activating Token Index: 187

Text #11

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.7661. Min Act: -0.0001

Data Index: 377729 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.8276. Min Act: -0.0001

Data Index: 1122297 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.7768. Min Act: -0.0001

Data Index: 1431277 (Python Code)

Max Activating Token Index: 672

Text #14

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.8124. Min Act: -0.0001

Data Index: 1449921 (Python Code)

Max Activating Token Index: 555

Text #15

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.8017. Min Act: -0.0001

Data Index: 1383800 (Python Code)

Max Activating Token Index: 80

Text #16

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.8021. Min Act: -0.0001

Data Index: 1527356 (Python Code)

Max Activating Token Index: 560

Text #17

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.7700. Min Act: -0.0001

Data Index: 1643215 (Python Code)

Max Activating Token Index: 689

Text #18

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.7827. Min Act: -0.0001

Data Index: 1580290 (Python Code)

Max Activating Token Index: 169

Text #19

Max Range: 0.8995. Min Range: -0.8995

Max Act: 0.7774. Min Act: -0.0001

Data Index: 491208 (C4 (Web Text))

Max Activating Token Index: 987