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

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

Neuron 615 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0093. Min Act: -0.0002

Data Index: 383689 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0093. Min Act: -0.0002

Data Index: 905168 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0091. Min Act: -0.0002

Data Index: 937613 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0089. Min Act: -0.0002

Data Index: 821261 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0088. Min Act: -0.0002

Data Index: 153678 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0088. Min Act: -0.0002

Data Index: 408167 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1245757 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1306514 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1357060 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1412830 (Python Code)

Max Activating Token Index: 673

Text #10

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0086. Min Act: -0.0002

Data Index: 513565 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0086. Min Act: -0.0002

Data Index: 1452421 (Python Code)

Max Activating Token Index: 2

Text #12

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0086. Min Act: -0.0002

Data Index: 89818 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1104774 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0086. Min Act: -0.0002

Data Index: 426735 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0086. Min Act: -0.0002

Data Index: 121314 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0086. Min Act: -0.0002

Data Index: 117018 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0085. Min Act: -0.0002

Data Index: 1145336 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0085. Min Act: -0.0002

Data Index: 895803 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0085. Min Act: -0.0002

Data Index: 795811 (C4 (Web Text))

Max Activating Token Index: 498