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

Dataset: The Pile

Neuron 2802 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: 0.9169. Min Range: -0.9169

Max Act: 0.9169. Min Act: -0.0000

Data Index: 581708 (The Pile)

Max Activating Token Index: 982

Text #1

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8799. Min Act: -0.0000

Data Index: 236309 (The Pile)

Max Activating Token Index: 1013

Text #2

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8338. Min Act: -0.0000

Data Index: 904461 (The Pile)

Max Activating Token Index: 523

Text #3

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8391. Min Act: -0.0000

Data Index: 491407 (The Pile)

Max Activating Token Index: 173

Text #4

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8084. Min Act: -0.0000

Data Index: 87134 (The Pile)

Max Activating Token Index: 270

Text #5

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.7588. Min Act: -0.0000

Data Index: 739347 (The Pile)

Max Activating Token Index: 532

Text #6

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.7610. Min Act: -0.0000

Data Index: 275480 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.7700. Min Act: -0.0000

Data Index: 40897 (The Pile)

Max Activating Token Index: 35

Text #8

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8124. Min Act: -0.0000

Data Index: 1791897 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.7721. Min Act: -0.0000

Data Index: 1851119 (The Pile)

Max Activating Token Index: 154

Text #10

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1825148 (The Pile)

Max Activating Token Index: 74

Text #11

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.7549. Min Act: -0.0000

Data Index: 1730616 (The Pile)

Max Activating Token Index: 257

Text #12

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.7940. Min Act: -0.0000

Data Index: 1410416 (The Pile)

Max Activating Token Index: 762

Text #13

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.7612. Min Act: -0.0000

Data Index: 256571 (The Pile)

Max Activating Token Index: 810

Text #14

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.6937. Min Act: -0.0000

Data Index: 295142 (The Pile)

Max Activating Token Index: 566

Text #15

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.7192. Min Act: -0.0000

Data Index: 533530 (The Pile)

Max Activating Token Index: 360

Text #16

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.6947. Min Act: -0.0000

Data Index: 1103347 (The Pile)

Max Activating Token Index: 651

Text #17

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.7596. Min Act: -0.0000

Data Index: 903597 (The Pile)

Max Activating Token Index: 186

Text #18

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.7081. Min Act: -0.0000

Data Index: 927144 (The Pile)

Max Activating Token Index: 765

Text #19

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.6783. Min Act: -0.0000

Data Index: 1823265 (The Pile)

Max Activating Token Index: 135