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

Dataset: The Pile

Neuron 2108 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0536. Min Range: -7.0536

Max Act: 7.0536. Min Act: -0.0000

Data Index: 1119805 (The Pile)

Max Activating Token Index: 463

Text #1

Max Range: 7.0536. Min Range: -7.0536

Max Act: 6.8851. Min Act: -0.0000

Data Index: 216578 (The Pile)

Max Activating Token Index: 406

Text #2

Max Range: 7.0536. Min Range: -7.0536

Max Act: 6.6648. Min Act: -0.0000

Data Index: 289937 (The Pile)

Max Activating Token Index: 801

Text #3

Max Range: 7.0536. Min Range: -7.0536

Max Act: 6.7471. Min Act: -0.0000

Data Index: 1201084 (The Pile)

Max Activating Token Index: 371

Text #4

Max Range: 7.0536. Min Range: -7.0536

Max Act: 5.9219. Min Act: -0.0000

Data Index: 315108 (The Pile)

Max Activating Token Index: 195

Text #5

Max Range: 7.0536. Min Range: -7.0536

Max Act: 6.2085. Min Act: -0.0000

Data Index: 1128588 (The Pile)

Max Activating Token Index: 979

Text #6

Max Range: 7.0536. Min Range: -7.0536

Max Act: 5.6814. Min Act: -0.0000

Data Index: 1055958 (The Pile)

Max Activating Token Index: 479

Text #7

Max Range: 7.0536. Min Range: -7.0536

Max Act: 5.6882. Min Act: -0.0000

Data Index: 1852352 (The Pile)

Max Activating Token Index: 258

Text #8

Max Range: 7.0536. Min Range: -7.0536

Max Act: 5.7535. Min Act: -0.0000

Data Index: 1666315 (The Pile)

Max Activating Token Index: 400

Text #9

Max Range: 7.0536. Min Range: -7.0536

Max Act: 5.8712. Min Act: -0.0000

Data Index: 598684 (The Pile)

Max Activating Token Index: 253

Text #10

Max Range: 7.0536. Min Range: -7.0536

Max Act: 5.2461. Min Act: -0.0000

Data Index: 656907 (The Pile)

Max Activating Token Index: 695

Text #11

Max Range: 7.0536. Min Range: -7.0536

Max Act: 5.3672. Min Act: -0.0000

Data Index: 511011 (The Pile)

Max Activating Token Index: 516

Text #12

Max Range: 7.0536. Min Range: -7.0536

Max Act: 5.4937. Min Act: -0.0000

Data Index: 1179519 (The Pile)

Max Activating Token Index: 595

Text #13

Max Range: 7.0536. Min Range: -7.0536

Max Act: 5.3143. Min Act: -0.0000

Data Index: 1089214 (The Pile)

Max Activating Token Index: 277

Text #14

Max Range: 7.0536. Min Range: -7.0536

Max Act: 5.4356. Min Act: -0.0000

Data Index: 1425279 (The Pile)

Max Activating Token Index: 281

Text #15

Max Range: 7.0536. Min Range: -7.0536

Max Act: 4.9741. Min Act: -0.0000

Data Index: 1118323 (The Pile)

Max Activating Token Index: 388

Text #16

Max Range: 7.0536. Min Range: -7.0536

Max Act: 4.9630. Min Act: -0.0000

Data Index: 1861944 (The Pile)

Max Activating Token Index: 907

Text #17

Max Range: 7.0536. Min Range: -7.0536

Max Act: 4.9382. Min Act: -0.0000

Data Index: 76110 (The Pile)

Max Activating Token Index: 502

Text #18

Max Range: 7.0536. Min Range: -7.0536

Max Act: 5.2877. Min Act: -0.0000

Data Index: 749536 (The Pile)

Max Activating Token Index: 1018

Text #19

Max Range: 7.0536. Min Range: -7.0536

Max Act: 4.6832. Min Act: -0.0000

Data Index: 1195202 (The Pile)

Max Activating Token Index: 553