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

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

Neuron 3878 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: 1.1061. Min Range: -1.1061

Max Act: 1.1061. Min Act: -0.0000

Data Index: 1355448 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 1.1061. Min Range: -1.1061

Max Act: 1.0276. Min Act: -0.0000

Data Index: 928092 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 1.1061. Min Range: -1.1061

Max Act: 1.0505. Min Act: -0.0000

Data Index: 441536 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 1.1061. Min Range: -1.1061

Max Act: 1.0514. Min Act: -0.0000

Data Index: 985785 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.9411. Min Act: -0.0000

Data Index: 782930 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.9717. Min Act: -0.0000

Data Index: 513053 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.9083. Min Act: -0.0000

Data Index: 747171 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.9138. Min Act: -0.0000

Data Index: 494285 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.9064. Min Act: -0.0000

Data Index: 632287 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.9613. Min Act: -0.0000

Data Index: 1321242 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.8592. Min Act: -0.0000

Data Index: 1064971 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.9041. Min Act: -0.0000

Data Index: 880004 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.8853. Min Act: -0.0000

Data Index: 1344294 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.8783. Min Act: -0.0000

Data Index: 94905 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.8589. Min Act: -0.0000

Data Index: 230082 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.9053. Min Act: -0.0000

Data Index: 307606 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.8586. Min Act: -0.0000

Data Index: 34970 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.9276. Min Act: -0.0000

Data Index: 233413 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.8677. Min Act: -0.0000

Data Index: 612407 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 1.1061. Min Range: -1.1061

Max Act: 0.9137. Min Act: -0.0000

Data Index: 1305326 (C4 (Web Text))

Max Activating Token Index: 521