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

Dataset: The Pile

Neuron 1536 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7774. Min Range: -1.7774

Max Act: 1.7774. Min Act: -0.0000

Data Index: 1481811 (The Pile)

Max Activating Token Index: 866

Text #1

Max Range: 1.7774. Min Range: -1.7774

Max Act: 1.6662. Min Act: -0.0000

Data Index: 930874 (The Pile)

Max Activating Token Index: 255

Text #2

Max Range: 1.7774. Min Range: -1.7774

Max Act: 1.4864. Min Act: -0.0000

Data Index: 347262 (The Pile)

Max Activating Token Index: 98

Text #3

Max Range: 1.7774. Min Range: -1.7774

Max Act: 1.5587. Min Act: -0.0000

Data Index: 434001 (The Pile)

Max Activating Token Index: 1007

Text #4

Max Range: 1.7774. Min Range: -1.7774

Max Act: 1.5640. Min Act: -0.0000

Data Index: 293524 (The Pile)

Max Activating Token Index: 225

Text #5

Max Range: 1.7774. Min Range: -1.7774

Max Act: 1.4978. Min Act: -0.0000

Data Index: 1899303 (The Pile)

Max Activating Token Index: 427

Text #6

Max Range: 1.7774. Min Range: -1.7774

Max Act: 1.4447. Min Act: -0.0000

Data Index: 928693 (The Pile)

Max Activating Token Index: 457

Text #7

Max Range: 1.7774. Min Range: -1.7774

Max Act: 1.4651. Min Act: -0.0000

Data Index: 719818 (The Pile)

Max Activating Token Index: 334

Text #8

Max Range: 1.7774. Min Range: -1.7774

Max Act: 1.5436. Min Act: -0.0000

Data Index: 94915 (The Pile)

Max Activating Token Index: 360

Text #9

Max Range: 1.7774. Min Range: -1.7774

Max Act: 1.4012. Min Act: -0.0000

Data Index: 332968 (The Pile)

Max Activating Token Index: 272

Text #10

Max Range: 1.7774. Min Range: -1.7774

Max Act: 1.4814. Min Act: -0.0000

Data Index: 1519877 (The Pile)

Max Activating Token Index: 389

Text #11

Max Range: 1.7774. Min Range: -1.7774

Max Act: 1.3405. Min Act: -0.0000

Data Index: 978977 (The Pile)

Max Activating Token Index: 93

Text #12

Max Range: 1.7774. Min Range: -1.7774

Max Act: 1.4204. Min Act: -0.0000

Data Index: 1414903 (The Pile)

Max Activating Token Index: 166

Text #13

Max Range: 1.7774. Min Range: -1.7774

Max Act: 1.3399. Min Act: -0.0000

Data Index: 1206903 (The Pile)

Max Activating Token Index: 158

Text #14

Max Range: 1.7774. Min Range: -1.7774

Max Act: 1.4964. Min Act: -0.0000

Data Index: 800082 (The Pile)

Max Activating Token Index: 514

Text #15

Max Range: 1.7774. Min Range: -1.7774

Max Act: 1.4657. Min Act: -0.0000

Data Index: 1680425 (The Pile)

Max Activating Token Index: 483

Text #16

Max Range: 1.7774. Min Range: -1.7774

Max Act: 1.3194. Min Act: -0.0000

Data Index: 1519344 (The Pile)

Max Activating Token Index: 103

Text #17

Max Range: 1.7774. Min Range: -1.7774

Max Act: 1.3515. Min Act: -0.0000

Data Index: 304403 (The Pile)

Max Activating Token Index: 260

Text #18

Max Range: 1.7774. Min Range: -1.7774

Max Act: 1.4574. Min Act: -0.0000

Data Index: 940927 (The Pile)

Max Activating Token Index: 428

Text #19

Max Range: 1.7774. Min Range: -1.7774

Max Act: 1.2051. Min Act: -0.0000

Data Index: 745482 (The Pile)

Max Activating Token Index: 208