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

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

Neuron 2385 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1209245 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0066. Min Act: -0.0004

Data Index: 431542 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0066. Min Act: -0.0004

Data Index: 382010 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0065. Min Act: -0.0004

Data Index: 455616 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0064. Min Act: -0.0003

Data Index: 56138 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0064. Min Act: -0.0004

Data Index: 1040985 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0064. Min Act: -0.0003

Data Index: 868650 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1287094 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0063. Min Act: -0.0003

Data Index: 228117 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0063. Min Act: -0.0003

Data Index: 254537 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0062. Min Act: -0.0003

Data Index: 79591 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0062. Min Act: -0.0003

Data Index: 846937 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0062. Min Act: -0.0003

Data Index: 1226157 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0061. Min Act: -0.0004

Data Index: 582964 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0061. Min Act: -0.0004

Data Index: 321030 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0061. Min Act: -0.0003

Data Index: 270236 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0062. Min Act: -0.0004

Data Index: 767937 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0062. Min Act: -0.0003

Data Index: 225501 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1074454 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0061. Min Act: -0.0003

Data Index: 440833 (C4 (Web Text))

Max Activating Token Index: 40