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

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

Neuron 2286 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1904. Min Act: -0.0001

Data Index: 1226225 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1683. Min Act: -0.0001

Data Index: 1060191 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1552. Min Act: -0.0001

Data Index: 764885 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1281. Min Act: -0.0001

Data Index: 695785 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1295. Min Act: -0.0001

Data Index: 785178 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1383. Min Act: -0.0001

Data Index: 716330 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1282. Min Act: -0.0001

Data Index: 47043 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1249. Min Act: -0.0001

Data Index: 670642 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1310520 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1146. Min Act: -0.0001

Data Index: 92021 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1083. Min Act: -0.0001

Data Index: 1298736 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1061. Min Act: -0.0001

Data Index: 151171 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1057. Min Act: -0.0001

Data Index: 726244 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.0947. Min Act: -0.0001

Data Index: 1128505 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1058. Min Act: -0.0001

Data Index: 532018 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.1032. Min Act: -0.0001

Data Index: 556712 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.0973. Min Act: -0.0001

Data Index: 263933 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.0903. Min Act: -0.0001

Data Index: 1020234 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.0954. Min Act: -0.0001

Data Index: 197950 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 0.1904. Min Range: -0.1904

Max Act: 0.0937. Min Act: -0.0001

Data Index: 916734 (C4 (Web Text))

Max Activating Token Index: 957