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

Dataset: The Pile

Neuron 1224 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.5298. Min Act: -0.0000

Data Index: 403263 (The Pile)

Max Activating Token Index: 478

Text #1

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4740. Min Act: -0.0000

Data Index: 573512 (The Pile)

Max Activating Token Index: 324

Text #2

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4258. Min Act: 0.0000

Data Index: 419856 (The Pile)

Max Activating Token Index: 741

Text #3

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4742. Min Act: -0.0000

Data Index: 243652 (The Pile)

Max Activating Token Index: 791

Text #4

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4393. Min Act: -0.0000

Data Index: 1374622 (The Pile)

Max Activating Token Index: 313

Text #5

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4361. Min Act: -0.0000

Data Index: 922674 (The Pile)

Max Activating Token Index: 394

Text #6

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4244. Min Act: -0.0000

Data Index: 14258 (The Pile)

Max Activating Token Index: 141

Text #7

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1841736 (The Pile)

Max Activating Token Index: 80

Text #8

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.3934. Min Act: -0.0000

Data Index: 6618 (The Pile)

Max Activating Token Index: 659

Text #9

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4044. Min Act: -0.0000

Data Index: 619540 (The Pile)

Max Activating Token Index: 51

Text #10

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4033. Min Act: -0.0000

Data Index: 1839913 (The Pile)

Max Activating Token Index: 201

Text #11

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1611192 (The Pile)

Max Activating Token Index: 53

Text #12

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4020. Min Act: -0.0000

Data Index: 91487 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4111. Min Act: -0.0000

Data Index: 116586 (The Pile)

Max Activating Token Index: 252

Text #14

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.3812. Min Act: -0.0000

Data Index: 284668 (The Pile)

Max Activating Token Index: 462

Text #15

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.3705. Min Act: -0.0000

Data Index: 1272062 (The Pile)

Max Activating Token Index: 26

Text #16

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.3825. Min Act: -0.0000

Data Index: 224033 (The Pile)

Max Activating Token Index: 403

Text #17

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4070. Min Act: -0.0000

Data Index: 1262147 (The Pile)

Max Activating Token Index: 412

Text #18

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.3851. Min Act: -0.0000

Data Index: 495478 (The Pile)

Max Activating Token Index: 892

Text #19

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.3954. Min Act: -0.0000

Data Index: 795766 (The Pile)

Max Activating Token Index: 47