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

Dataset: The Pile

Neuron 385 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7782. Min Range: -1.7782

Max Act: 1.7782. Min Act: -0.0000

Data Index: 474125 (The Pile)

Max Activating Token Index: 525

Text #1

Max Range: 1.7782. Min Range: -1.7782

Max Act: 1.5027. Min Act: -0.0000

Data Index: 1243316 (The Pile)

Max Activating Token Index: 101

Text #2

Max Range: 1.7782. Min Range: -1.7782

Max Act: 1.5476. Min Act: -0.0000

Data Index: 1573258 (The Pile)

Max Activating Token Index: 757

Text #3

Max Range: 1.7782. Min Range: -1.7782

Max Act: 1.4806. Min Act: -0.0000

Data Index: 1321178 (The Pile)

Max Activating Token Index: 694

Text #4

Max Range: 1.7782. Min Range: -1.7782

Max Act: 1.4592. Min Act: -0.0000

Data Index: 759232 (The Pile)

Max Activating Token Index: 236

Text #5

Max Range: 1.7782. Min Range: -1.7782

Max Act: 1.4458. Min Act: 0.0000

Data Index: 396454 (The Pile)

Max Activating Token Index: 843

Text #6

Max Range: 1.7782. Min Range: -1.7782

Max Act: 1.3730. Min Act: -0.0000

Data Index: 362330 (The Pile)

Max Activating Token Index: 478

Text #7

Max Range: 1.7782. Min Range: -1.7782

Max Act: 1.4291. Min Act: 0.0000

Data Index: 228208 (The Pile)

Max Activating Token Index: 242

Text #8

Max Range: 1.7782. Min Range: -1.7782

Max Act: 1.3848. Min Act: 0.0000

Data Index: 1387938 (The Pile)

Max Activating Token Index: 404

Text #9

Max Range: 1.7782. Min Range: -1.7782

Max Act: 1.3026. Min Act: -0.0000

Data Index: 686956 (The Pile)

Max Activating Token Index: 133

Text #10

Max Range: 1.7782. Min Range: -1.7782

Max Act: 1.3677. Min Act: -0.0000

Data Index: 966360 (The Pile)

Max Activating Token Index: 375

Text #11

Max Range: 1.7782. Min Range: -1.7782

Max Act: 1.3817. Min Act: -0.0000

Data Index: 1515761 (The Pile)

Max Activating Token Index: 317

Text #12

Max Range: 1.7782. Min Range: -1.7782

Max Act: 1.4544. Min Act: 0.0000

Data Index: 360510 (The Pile)

Max Activating Token Index: 521

Text #13

Max Range: 1.7782. Min Range: -1.7782

Max Act: 1.3647. Min Act: -0.0000

Data Index: 63610 (The Pile)

Max Activating Token Index: 975

Text #14

Max Range: 1.7782. Min Range: -1.7782

Max Act: 1.3420. Min Act: -0.0000

Data Index: 240375 (The Pile)

Max Activating Token Index: 438

Text #15

Max Range: 1.7782. Min Range: -1.7782

Max Act: 1.3440. Min Act: -0.0000

Data Index: 1871632 (The Pile)

Max Activating Token Index: 485

Text #16

Max Range: 1.7782. Min Range: -1.7782

Max Act: 1.2756. Min Act: 0.0000

Data Index: 1906460 (The Pile)

Max Activating Token Index: 269

Text #17

Max Range: 1.7782. Min Range: -1.7782

Max Act: 1.3315. Min Act: -0.0000

Data Index: 179711 (The Pile)

Max Activating Token Index: 236

Text #18

Max Range: 1.7782. Min Range: -1.7782

Max Act: 1.3336. Min Act: -0.0000

Data Index: 1748871 (The Pile)

Max Activating Token Index: 383

Text #19

Max Range: 1.7782. Min Range: -1.7782

Max Act: 1.2331. Min Act: 0.0000

Data Index: 913128 (The Pile)

Max Activating Token Index: 404