Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2057 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4848. Min Range: -2.4848

Max Act: 2.4683. Min Act: -0.0000

Data Index: 715932 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 2.4848. Min Range: -2.4848

Max Act: 2.3459. Min Act: -0.0000

Data Index: 1479789 (Python Code)

Max Activating Token Index: 472

Text #2

Max Range: 2.4848. Min Range: -2.4848

Max Act: 2.3341. Min Act: -0.0000

Data Index: 1531045 (Python Code)

Max Activating Token Index: 590

Text #3

Max Range: 2.4848. Min Range: -2.4848

Max Act: 2.2174. Min Act: -0.0000

Data Index: 138335 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 2.4848. Min Range: -2.4848

Max Act: 2.2819. Min Act: -0.0000

Data Index: 473468 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 2.4848. Min Range: -2.4848

Max Act: 2.4848. Min Act: -0.0000

Data Index: 1524251 (Python Code)

Max Activating Token Index: 851

Text #6

Max Range: 2.4848. Min Range: -2.4848

Max Act: 2.0916. Min Act: -0.0000

Data Index: 989626 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 2.4848. Min Range: -2.4848

Max Act: 2.2945. Min Act: -0.0000

Data Index: 1434976 (Python Code)

Max Activating Token Index: 543

Text #8

Max Range: 2.4848. Min Range: -2.4848

Max Act: 2.2990. Min Act: -0.0000

Data Index: 1386269 (Python Code)

Max Activating Token Index: 894

Text #9

Max Range: 2.4848. Min Range: -2.4848

Max Act: 2.0505. Min Act: -0.0000

Data Index: 198001 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 2.4848. Min Range: -2.4848

Max Act: 1.9809. Min Act: -0.0000

Data Index: 1579076 (Python Code)

Max Activating Token Index: 275

Text #11

Max Range: 2.4848. Min Range: -2.4848

Max Act: 2.1348. Min Act: -0.0000

Data Index: 1578048 (Python Code)

Max Activating Token Index: 988

Text #12

Max Range: 2.4848. Min Range: -2.4848

Max Act: 2.1389. Min Act: -0.0000

Data Index: 1233322 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 2.4848. Min Range: -2.4848

Max Act: 2.1085. Min Act: -0.0000

Data Index: 1632661 (Python Code)

Max Activating Token Index: 743

Text #14

Max Range: 2.4848. Min Range: -2.4848

Max Act: 2.0054. Min Act: -0.0000

Data Index: 1367081 (Python Code)

Max Activating Token Index: 727

Text #15

Max Range: 2.4848. Min Range: -2.4848

Max Act: 2.0047. Min Act: -0.0000

Data Index: 1522213 (Python Code)

Max Activating Token Index: 427

Text #16

Max Range: 2.4848. Min Range: -2.4848

Max Act: 1.8818. Min Act: -0.0000

Data Index: 1546555 (Python Code)

Max Activating Token Index: 47

Text #17

Max Range: 2.4848. Min Range: -2.4848

Max Act: 1.9748. Min Act: -0.0000

Data Index: 1457932 (Python Code)

Max Activating Token Index: 647

Text #18

Max Range: 2.4848. Min Range: -2.4848

Max Act: 2.0799. Min Act: -0.0000

Data Index: 1226705 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 2.4848. Min Range: -2.4848

Max Act: 2.0657. Min Act: -0.0000

Data Index: 1500223 (Python Code)

Max Activating Token Index: 736