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

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

Neuron 2554 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: 0.1263. Min Range: -0.1263

Max Act: 0.1263. Min Act: -0.0001

Data Index: 453321 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1134. Min Act: -0.0001

Data Index: 1121064 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1120. Min Act: -0.0001

Data Index: 1036963 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0959. Min Act: -0.0001

Data Index: 907502 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1015. Min Act: -0.0001

Data Index: 589561 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1012. Min Act: -0.0001

Data Index: 88997 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0995. Min Act: -0.0001

Data Index: 258008 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0944. Min Act: -0.0001

Data Index: 422223 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1245930 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0970. Min Act: -0.0001

Data Index: 486063 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0931. Min Act: -0.0001

Data Index: 998093 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1145052 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0964. Min Act: -0.0001

Data Index: 882496 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0957. Min Act: -0.0001

Data Index: 854453 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0990. Min Act: -0.0001

Data Index: 588968 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0911. Min Act: -0.0001

Data Index: 803864 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0911. Min Act: -0.0001

Data Index: 746872 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0907. Min Act: -0.0001

Data Index: 393135 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0911. Min Act: -0.0001

Data Index: 937245 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0923. Min Act: -0.0001

Data Index: 39 (C4 (Web Text))

Max Activating Token Index: 202