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

Dataset: The Pile

Neuron 1268 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: 1.6523. Min Range: -1.6523

Max Act: 1.5761. Min Act: -0.0000

Data Index: 777217 (The Pile)

Max Activating Token Index: 471

Text #1

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.6481. Min Act: -0.0000

Data Index: 1508719 (The Pile)

Max Activating Token Index: 152

Text #2

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.6523. Min Act: -0.0000

Data Index: 1729932 (The Pile)

Max Activating Token Index: 482

Text #3

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.5648. Min Act: -0.0000

Data Index: 849026 (The Pile)

Max Activating Token Index: 430

Text #4

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.5779. Min Act: -0.0000

Data Index: 494938 (The Pile)

Max Activating Token Index: 287

Text #5

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.5699. Min Act: -0.0000

Data Index: 196632 (The Pile)

Max Activating Token Index: 272

Text #6

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.5469. Min Act: -0.0000

Data Index: 1147537 (The Pile)

Max Activating Token Index: 940

Text #7

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.4786. Min Act: -0.0000

Data Index: 789940 (The Pile)

Max Activating Token Index: 299

Text #8

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.4105. Min Act: -0.0000

Data Index: 717941 (The Pile)

Max Activating Token Index: 230

Text #9

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.3996. Min Act: -0.0000

Data Index: 1969606 (The Pile)

Max Activating Token Index: 528

Text #10

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.4289. Min Act: -0.0000

Data Index: 1243811 (The Pile)

Max Activating Token Index: 668

Text #11

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.5119. Min Act: -0.0000

Data Index: 1073489 (The Pile)

Max Activating Token Index: 407

Text #12

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.4675. Min Act: -0.0000

Data Index: 980788 (The Pile)

Max Activating Token Index: 669

Text #13

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.6382. Min Act: -0.0000

Data Index: 54083 (The Pile)

Max Activating Token Index: 296

Text #14

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.3762. Min Act: -0.0000

Data Index: 211687 (The Pile)

Max Activating Token Index: 721

Text #15

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.4595. Min Act: -0.0000

Data Index: 1888077 (The Pile)

Max Activating Token Index: 238

Text #16

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.4880. Min Act: -0.0000

Data Index: 602660 (The Pile)

Max Activating Token Index: 263

Text #17

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.4473. Min Act: -0.0000

Data Index: 1221563 (The Pile)

Max Activating Token Index: 537

Text #18

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.3660. Min Act: -0.0000

Data Index: 797536 (The Pile)

Max Activating Token Index: 390

Text #19

Max Range: 1.6523. Min Range: -1.6523

Max Act: 1.3498. Min Act: -0.0000

Data Index: 1662287 (The Pile)

Max Activating Token Index: 675