Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3017 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3952. Min Act: -0.0001

Data Index: 1181919 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3829. Min Act: -0.0001

Data Index: 522294 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3810. Min Act: -0.0001

Data Index: 233165 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3793. Min Act: -0.0001

Data Index: 1024503 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3731. Min Act: -0.0001

Data Index: 878560 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3742. Min Act: -0.0001

Data Index: 1221615 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3621. Min Act: -0.0001

Data Index: 413141 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3597. Min Act: -0.0001

Data Index: 694457 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3567. Min Act: -0.0001

Data Index: 1247390 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3579. Min Act: -0.0001

Data Index: 690375 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3464. Min Act: -0.0001

Data Index: 273185 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3454. Min Act: -0.0001

Data Index: 121276 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3600. Min Act: -0.0001

Data Index: 742110 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3588. Min Act: -0.0001

Data Index: 936812 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3571. Min Act: -0.0001

Data Index: 359376 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3676. Min Act: -0.0001

Data Index: 1062227 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3515. Min Act: -0.0001

Data Index: 665001 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3495. Min Act: -0.0001

Data Index: 1318964 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3408. Min Act: -0.0001

Data Index: 1047711 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.3952. Min Range: -0.3952

Max Act: 0.3390. Min Act: -0.0001

Data Index: 1063719 (C4 (Web Text))

Max Activating Token Index: 71