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

Dataset: The Pile

Neuron 1107 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.7595. Min Act: -0.0000

Data Index: 1054104 (The Pile)

Max Activating Token Index: 567

Text #1

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.6849. Min Act: -0.0000

Data Index: 267682 (The Pile)

Max Activating Token Index: 122

Text #2

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1150384 (The Pile)

Max Activating Token Index: 123

Text #3

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5376. Min Act: -0.0000

Data Index: 195078 (The Pile)

Max Activating Token Index: 463

Text #4

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5929. Min Act: -0.0000

Data Index: 224138 (The Pile)

Max Activating Token Index: 93

Text #5

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5437. Min Act: -0.0000

Data Index: 449736 (The Pile)

Max Activating Token Index: 599

Text #6

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5817. Min Act: -0.0000

Data Index: 614388 (The Pile)

Max Activating Token Index: 546

Text #7

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.6470. Min Act: -0.0000

Data Index: 1762455 (The Pile)

Max Activating Token Index: 301

Text #8

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5509. Min Act: -0.0000

Data Index: 1293554 (The Pile)

Max Activating Token Index: 529

Text #9

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5557. Min Act: -0.0000

Data Index: 1480599 (The Pile)

Max Activating Token Index: 538

Text #10

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.6038. Min Act: -0.0000

Data Index: 340453 (The Pile)

Max Activating Token Index: 130

Text #11

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.6250. Min Act: -0.0000

Data Index: 850115 (The Pile)

Max Activating Token Index: 990

Text #12

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1789149 (The Pile)

Max Activating Token Index: 448

Text #13

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5931. Min Act: -0.0000

Data Index: 429466 (The Pile)

Max Activating Token Index: 520

Text #14

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5346. Min Act: -0.0000

Data Index: 907869 (The Pile)

Max Activating Token Index: 702

Text #15

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5669. Min Act: -0.0000

Data Index: 1755325 (The Pile)

Max Activating Token Index: 754

Text #16

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1384500 (The Pile)

Max Activating Token Index: 242

Text #17

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5697. Min Act: -0.0000

Data Index: 1459802 (The Pile)

Max Activating Token Index: 901

Text #18

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5284. Min Act: 0.0000

Data Index: 570044 (The Pile)

Max Activating Token Index: 454

Text #19

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1998935 (The Pile)

Max Activating Token Index: 201