Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4028 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3457. Min Act: -0.0000

Data Index: 1936210 (The Pile)

Max Activating Token Index: 222

Text #1

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3336. Min Act: -0.0000

Data Index: 161360 (The Pile)

Max Activating Token Index: 514

Text #2

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3060. Min Act: -0.0000

Data Index: 89761 (The Pile)

Max Activating Token Index: 906

Text #3

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3114. Min Act: -0.0000

Data Index: 190665 (The Pile)

Max Activating Token Index: 382

Text #4

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3100. Min Act: -0.0000

Data Index: 1940064 (The Pile)

Max Activating Token Index: 410

Text #5

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3154. Min Act: -0.0000

Data Index: 131594 (The Pile)

Max Activating Token Index: 852

Text #6

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3005. Min Act: -0.0000

Data Index: 804562 (The Pile)

Max Activating Token Index: 774

Text #7

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2997. Min Act: -0.0000

Data Index: 1603316 (The Pile)

Max Activating Token Index: 565

Text #8

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3157. Min Act: -0.0000

Data Index: 105273 (The Pile)

Max Activating Token Index: 873

Text #9

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2897. Min Act: -0.0000

Data Index: 1362165 (The Pile)

Max Activating Token Index: 111

Text #10

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2771. Min Act: -0.0000

Data Index: 227605 (The Pile)

Max Activating Token Index: 338

Text #11

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3055. Min Act: -0.0000

Data Index: 513987 (The Pile)

Max Activating Token Index: 885

Text #12

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2834. Min Act: -0.0000

Data Index: 1892938 (The Pile)

Max Activating Token Index: 289

Text #13

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2744. Min Act: -0.0000

Data Index: 772005 (The Pile)

Max Activating Token Index: 743

Text #14

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2708. Min Act: -0.0000

Data Index: 921199 (The Pile)

Max Activating Token Index: 521

Text #15

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2901. Min Act: -0.0000

Data Index: 979973 (The Pile)

Max Activating Token Index: 424

Text #16

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2802. Min Act: -0.0000

Data Index: 104048 (The Pile)

Max Activating Token Index: 449

Text #17

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2690. Min Act: -0.0000

Data Index: 740896 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2981. Min Act: -0.0000

Data Index: 156283 (The Pile)

Max Activating Token Index: 544

Text #19

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2771. Min Act: -0.0000

Data Index: 719581 (The Pile)

Max Activating Token Index: 421