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

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

Neuron 3937 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5989. Min Range: -2.5989

Max Act: 2.5354. Min Act: -0.0000

Data Index: 1384502 (Python Code)

Max Activating Token Index: 226

Text #1

Max Range: 2.5989. Min Range: -2.5989

Max Act: 2.5989. Min Act: -0.0000

Data Index: 1456983 (Python Code)

Max Activating Token Index: 927

Text #2

Max Range: 2.5989. Min Range: -2.5989

Max Act: 2.1946. Min Act: -0.0000

Data Index: 1426967 (Python Code)

Max Activating Token Index: 167

Text #3

Max Range: 2.5989. Min Range: -2.5989

Max Act: 2.3089. Min Act: -0.0000

Data Index: 1506820 (Python Code)

Max Activating Token Index: 96

Text #4

Max Range: 2.5989. Min Range: -2.5989

Max Act: 2.3948. Min Act: -0.0000

Data Index: 1472983 (Python Code)

Max Activating Token Index: 61

Text #5

Max Range: 2.5989. Min Range: -2.5989

Max Act: 2.2305. Min Act: -0.0000

Data Index: 1475759 (Python Code)

Max Activating Token Index: 760

Text #6

Max Range: 2.5989. Min Range: -2.5989

Max Act: 2.3164. Min Act: -0.0000

Data Index: 1626643 (Python Code)

Max Activating Token Index: 410

Text #7

Max Range: 2.5989. Min Range: -2.5989

Max Act: 2.4061. Min Act: -0.0000

Data Index: 1534071 (Python Code)

Max Activating Token Index: 194

Text #8

Max Range: 2.5989. Min Range: -2.5989

Max Act: 2.2784. Min Act: -0.0000

Data Index: 616512 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 2.5989. Min Range: -2.5989

Max Act: 2.1826. Min Act: -0.0000

Data Index: 45228 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 2.5989. Min Range: -2.5989

Max Act: 2.0533. Min Act: -0.0000

Data Index: 949290 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 2.5989. Min Range: -2.5989

Max Act: 2.1589. Min Act: -0.0000

Data Index: 1386718 (Python Code)

Max Activating Token Index: 416

Text #12

Max Range: 2.5989. Min Range: -2.5989

Max Act: 2.1418. Min Act: -0.0000

Data Index: 765932 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 2.5989. Min Range: -2.5989

Max Act: 2.0084. Min Act: -0.0000

Data Index: 966751 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 2.5989. Min Range: -2.5989

Max Act: 2.0736. Min Act: -0.0000

Data Index: 447457 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 2.5989. Min Range: -2.5989

Max Act: 2.0716. Min Act: -0.0000

Data Index: 1630396 (Python Code)

Max Activating Token Index: 317

Text #16

Max Range: 2.5989. Min Range: -2.5989

Max Act: 2.1500. Min Act: -0.0000

Data Index: 7453 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 2.5989. Min Range: -2.5989

Max Act: 2.0377. Min Act: -0.0000

Data Index: 1189489 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 2.5989. Min Range: -2.5989

Max Act: 1.9148. Min Act: -0.0000

Data Index: 31506 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 2.5989. Min Range: -2.5989

Max Act: 2.0114. Min Act: -0.0000

Data Index: 1277978 (C4 (Web Text))

Max Activating Token Index: 74