Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1000 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0097. Min Act: -0.0006

Data Index: 539472 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0077. Min Act: -0.0006

Data Index: 1059066 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0078. Min Act: -0.0006

Data Index: 946569 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0073. Min Act: -0.0006

Data Index: 381659 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0072. Min Act: -0.0006

Data Index: 871000 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0073. Min Act: -0.0006

Data Index: 736676 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0074. Min Act: -0.0006

Data Index: 1265830 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0072. Min Act: -0.0006

Data Index: 864409 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0070. Min Act: -0.0006

Data Index: 637886 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0069. Min Act: -0.0006

Data Index: 1020633 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0065. Min Act: -0.0006

Data Index: 1258372 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0071. Min Act: -0.0006

Data Index: 80197 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0070. Min Act: -0.0006

Data Index: 132221 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0067. Min Act: -0.0006

Data Index: 319172 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0067. Min Act: -0.0006

Data Index: 476963 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0067. Min Act: -0.0006

Data Index: 212950 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0070. Min Act: -0.0006

Data Index: 613057 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0066. Min Act: -0.0006

Data Index: 163987 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0069. Min Act: -0.0006

Data Index: 525672 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.0097. Min Range: -0.0097

Max Act: 0.0065. Min Act: -0.0006

Data Index: 948208 (C4 (Web Text))

Max Activating Token Index: 438