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

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

Neuron 2027 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: 0.1145. Min Range: -0.1145

Max Act: 0.1119. Min Act: -0.0001

Data Index: 374950 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1072. Min Act: -0.0001

Data Index: 1210000 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1065. Min Act: -0.0001

Data Index: 1216855 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1056. Min Act: -0.0001

Data Index: 736874 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1145. Min Act: -0.0001

Data Index: 218027 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0979. Min Act: -0.0001

Data Index: 1273650 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1066. Min Act: -0.0001

Data Index: 771339 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1026. Min Act: -0.0001

Data Index: 793965 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0988. Min Act: -0.0001

Data Index: 99412 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0941. Min Act: -0.0001

Data Index: 310058 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0957. Min Act: -0.0001

Data Index: 289840 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1035. Min Act: -0.0001

Data Index: 130443 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1013. Min Act: -0.0001

Data Index: 996475 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1009. Min Act: -0.0001

Data Index: 664969 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0957. Min Act: -0.0001

Data Index: 972737 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0882. Min Act: -0.0001

Data Index: 1192216 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0946. Min Act: -0.0001

Data Index: 213996 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0936. Min Act: -0.0001

Data Index: 139043 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1271100 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0965. Min Act: -0.0001

Data Index: 232857 (C4 (Web Text))

Max Activating Token Index: 399