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

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

Neuron 4607 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0046. Min Range: -1.0046

Max Act: 1.0046. Min Act: -0.0000

Data Index: 658543 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.8317. Min Act: 0.0000

Data Index: 759880 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.8269. Min Act: -0.0000

Data Index: 818467 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.8133. Min Act: -0.0000

Data Index: 598226 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.8077. Min Act: -0.0000

Data Index: 1197635 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.7996. Min Act: -0.0000

Data Index: 1168142 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.7981. Min Act: -0.0000

Data Index: 1196664 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.7830. Min Act: -0.0000

Data Index: 614702 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.7408. Min Act: -0.0000

Data Index: 893042 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.7477. Min Act: 0.0000

Data Index: 223322 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.7028. Min Act: -0.0000

Data Index: 363387 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.7130. Min Act: 0.0002

Data Index: 1172522 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.7055. Min Act: -0.0000

Data Index: 804805 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.7140. Min Act: 0.0001

Data Index: 221117 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.7114. Min Act: -0.0000

Data Index: 299305 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.6890. Min Act: 0.0000

Data Index: 681742 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.6769. Min Act: -0.0000

Data Index: 688693 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.6957. Min Act: -0.0000

Data Index: 334982 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.6938. Min Act: -0.0000

Data Index: 917455 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.6703. Min Act: 0.0000

Data Index: 1315420 (C4 (Web Text))

Max Activating Token Index: 615