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

Dataset: The Pile

Neuron 5023 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1827134 (The Pile)

Max Activating Token Index: 400

Text #1

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3567. Min Act: -0.0000

Data Index: 317221 (The Pile)

Max Activating Token Index: 297

Text #2

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1097779 (The Pile)

Max Activating Token Index: 131

Text #3

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3223. Min Act: -0.0000

Data Index: 1212882 (The Pile)

Max Activating Token Index: 478

Text #4

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1317326 (The Pile)

Max Activating Token Index: 119

Text #5

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.3031. Min Act: -0.0000

Data Index: 1240816 (The Pile)

Max Activating Token Index: 337

Text #6

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2968. Min Act: -0.0000

Data Index: 1576281 (The Pile)

Max Activating Token Index: 250

Text #7

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2983. Min Act: -0.0000

Data Index: 1422935 (The Pile)

Max Activating Token Index: 559

Text #8

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1293541 (The Pile)

Max Activating Token Index: 280

Text #9

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2508. Min Act: -0.0000

Data Index: 1218812 (The Pile)

Max Activating Token Index: 418

Text #10

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2738. Min Act: -0.0000

Data Index: 1692039 (The Pile)

Max Activating Token Index: 227

Text #11

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2709. Min Act: -0.0000

Data Index: 1224033 (The Pile)

Max Activating Token Index: 254

Text #12

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2539. Min Act: -0.0000

Data Index: 1055936 (The Pile)

Max Activating Token Index: 527

Text #13

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2441. Min Act: -0.0000

Data Index: 44872 (The Pile)

Max Activating Token Index: 552

Text #14

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2771. Min Act: -0.0000

Data Index: 1711046 (The Pile)

Max Activating Token Index: 311

Text #15

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2548. Min Act: -0.0000

Data Index: 802095 (The Pile)

Max Activating Token Index: 254

Text #16

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2725. Min Act: -0.0000

Data Index: 1375709 (The Pile)

Max Activating Token Index: 205

Text #17

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1632749 (The Pile)

Max Activating Token Index: 191

Text #18

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2617. Min Act: -0.0000

Data Index: 962705 (The Pile)

Max Activating Token Index: 261

Text #19

Max Range: 0.4013. Min Range: -0.4013

Max Act: 0.2621. Min Act: -0.0000

Data Index: 1403236 (The Pile)

Max Activating Token Index: 161