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

Dataset: The Pile

Neuron 3518 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: 0.3822. Min Range: -0.3822

Max Act: 0.3366. Min Act: -0.0000

Data Index: 933542 (The Pile)

Max Activating Token Index: 580

Text #1

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3668. Min Act: -0.0000

Data Index: 1982978 (The Pile)

Max Activating Token Index: 743

Text #2

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3653. Min Act: -0.0001

Data Index: 207010 (The Pile)

Max Activating Token Index: 326

Text #3

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3822. Min Act: -0.0000

Data Index: 1622241 (The Pile)

Max Activating Token Index: 871

Text #4

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3059. Min Act: -0.0000

Data Index: 1792895 (The Pile)

Max Activating Token Index: 728

Text #5

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3423. Min Act: -0.0000

Data Index: 180126 (The Pile)

Max Activating Token Index: 275

Text #6

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3302. Min Act: -0.0000

Data Index: 1817757 (The Pile)

Max Activating Token Index: 370

Text #7

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3194. Min Act: -0.0000

Data Index: 253389 (The Pile)

Max Activating Token Index: 649

Text #8

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3062. Min Act: -0.0000

Data Index: 353147 (The Pile)

Max Activating Token Index: 482

Text #9

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.2707. Min Act: -0.0000

Data Index: 1939756 (The Pile)

Max Activating Token Index: 582

Text #10

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.2909. Min Act: -0.0000

Data Index: 127950 (The Pile)

Max Activating Token Index: 269

Text #11

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3089. Min Act: -0.0000

Data Index: 502047 (The Pile)

Max Activating Token Index: 948

Text #12

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.2970. Min Act: -0.0000

Data Index: 1748999 (The Pile)

Max Activating Token Index: 522

Text #13

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.2858. Min Act: -0.0000

Data Index: 1288191 (The Pile)

Max Activating Token Index: 164

Text #14

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.2795. Min Act: -0.0000

Data Index: 94113 (The Pile)

Max Activating Token Index: 50

Text #15

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3079. Min Act: -0.0000

Data Index: 400795 (The Pile)

Max Activating Token Index: 181

Text #16

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.2716. Min Act: -0.0000

Data Index: 11444 (The Pile)

Max Activating Token Index: 54

Text #17

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1653359 (The Pile)

Max Activating Token Index: 580

Text #18

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.2766. Min Act: -0.0000

Data Index: 1535755 (The Pile)

Max Activating Token Index: 771

Text #19

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.2616. Min Act: -0.0000

Data Index: 1367248 (The Pile)

Max Activating Token Index: 605