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

Dataset: The Pile

Neuron 4428 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.6677. Min Act: -0.0000

Data Index: 219428 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.6073. Min Act: -0.0000

Data Index: 359483 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5568. Min Act: -0.0000

Data Index: 44084 (The Pile)

Max Activating Token Index: 458

Text #3

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5728. Min Act: -0.0000

Data Index: 162370 (The Pile)

Max Activating Token Index: 306

Text #4

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1883945 (The Pile)

Max Activating Token Index: 441

Text #5

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.6029. Min Act: -0.0000

Data Index: 171503 (The Pile)

Max Activating Token Index: 50

Text #6

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1331690 (The Pile)

Max Activating Token Index: 142

Text #7

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1229384 (The Pile)

Max Activating Token Index: 442

Text #8

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5321. Min Act: -0.0000

Data Index: 1984665 (The Pile)

Max Activating Token Index: 780

Text #9

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5592. Min Act: -0.0000

Data Index: 566713 (The Pile)

Max Activating Token Index: 233

Text #10

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5828. Min Act: -0.0000

Data Index: 1374920 (The Pile)

Max Activating Token Index: 348

Text #11

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5673. Min Act: -0.0000

Data Index: 1559986 (The Pile)

Max Activating Token Index: 94

Text #12

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5538. Min Act: -0.0000

Data Index: 847217 (The Pile)

Max Activating Token Index: 172

Text #13

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5329. Min Act: -0.0000

Data Index: 593873 (The Pile)

Max Activating Token Index: 332

Text #14

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5749. Min Act: -0.0000

Data Index: 78589 (The Pile)

Max Activating Token Index: 556

Text #15

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5050. Min Act: -0.0000

Data Index: 322129 (The Pile)

Max Activating Token Index: 710

Text #16

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.4945. Min Act: -0.0000

Data Index: 1664367 (The Pile)

Max Activating Token Index: 380

Text #17

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5192. Min Act: -0.0000

Data Index: 244628 (The Pile)

Max Activating Token Index: 359

Text #18

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5107. Min Act: -0.0000

Data Index: 1851688 (The Pile)

Max Activating Token Index: 463

Text #19

Max Range: 0.6677. Min Range: -0.6677

Max Act: 0.5860. Min Act: -0.0000

Data Index: 222652 (The Pile)

Max Activating Token Index: 166