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

Dataset: The Pile

Neuron 2301 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.9826. Min Act: -0.0000

Data Index: 645043 (The Pile)

Max Activating Token Index: 902

Text #1

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.8491. Min Act: -0.0000

Data Index: 1272494 (The Pile)

Max Activating Token Index: 897

Text #2

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7599. Min Act: -0.0000

Data Index: 1081736 (The Pile)

Max Activating Token Index: 970

Text #3

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7875. Min Act: -0.0000

Data Index: 1981312 (The Pile)

Max Activating Token Index: 244

Text #4

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7874. Min Act: -0.0000

Data Index: 654678 (The Pile)

Max Activating Token Index: 489

Text #5

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1069260 (The Pile)

Max Activating Token Index: 196

Text #6

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7175. Min Act: -0.0000

Data Index: 1535070 (The Pile)

Max Activating Token Index: 69

Text #7

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7166. Min Act: -0.0000

Data Index: 327149 (The Pile)

Max Activating Token Index: 44

Text #8

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7074. Min Act: -0.0000

Data Index: 538136 (The Pile)

Max Activating Token Index: 222

Text #9

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1239432 (The Pile)

Max Activating Token Index: 604

Text #10

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7142. Min Act: -0.0000

Data Index: 469330 (The Pile)

Max Activating Token Index: 476

Text #11

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7049. Min Act: -0.0000

Data Index: 65297 (The Pile)

Max Activating Token Index: 159

Text #12

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7703. Min Act: -0.0000

Data Index: 339634 (The Pile)

Max Activating Token Index: 833

Text #13

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6996. Min Act: -0.0000

Data Index: 216026 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7149. Min Act: -0.0000

Data Index: 1376282 (The Pile)

Max Activating Token Index: 468

Text #15

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6980. Min Act: -0.0000

Data Index: 768343 (The Pile)

Max Activating Token Index: 1021

Text #16

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6286. Min Act: -0.0000

Data Index: 467471 (The Pile)

Max Activating Token Index: 662

Text #17

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7271. Min Act: -0.0000

Data Index: 665898 (The Pile)

Max Activating Token Index: 86

Text #18

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6861. Min Act: -0.0000

Data Index: 1699909 (The Pile)

Max Activating Token Index: 150

Text #19

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1909273 (The Pile)

Max Activating Token Index: 634