Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2597 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0788. Min Act: -0.0001

Data Index: 928205 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0815. Min Act: -0.0001

Data Index: 437751 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0739. Min Act: -0.0001

Data Index: 983171 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0755. Min Act: -0.0000

Data Index: 1062124 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0752. Min Act: -0.0001

Data Index: 430925 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0706. Min Act: -0.0001

Data Index: 1150683 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0681. Min Act: -0.0001

Data Index: 1217078 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1585243 (Python Code)

Max Activating Token Index: 643

Text #8

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0664. Min Act: -0.0001

Data Index: 689613 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0685. Min Act: -0.0000

Data Index: 1330189 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0706. Min Act: -0.0001

Data Index: 853204 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0650. Min Act: -0.0001

Data Index: 931389 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0723. Min Act: -0.0001

Data Index: 1233162 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0648. Min Act: -0.0001

Data Index: 598231 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0615. Min Act: -0.0001

Data Index: 1643966 (Python Code)

Max Activating Token Index: 830

Text #15

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0592. Min Act: -0.0001

Data Index: 1272479 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0650. Min Act: -0.0001

Data Index: 437685 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0620. Min Act: -0.0001

Data Index: 909845 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0616. Min Act: -0.0001

Data Index: 601589 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0592. Min Act: -0.0001

Data Index: 1401255 (Python Code)

Max Activating Token Index: 162