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

Dataset: The Pile

Neuron 2063 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.5624. Min Act: -0.0000

Data Index: 333390 (The Pile)

Max Activating Token Index: 160

Text #1

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4912. Min Act: -0.0000

Data Index: 883633 (The Pile)

Max Activating Token Index: 571

Text #2

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4542. Min Act: -0.0000

Data Index: 498023 (The Pile)

Max Activating Token Index: 815

Text #3

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4153. Min Act: -0.0000

Data Index: 899012 (The Pile)

Max Activating Token Index: 284

Text #4

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1773078 (The Pile)

Max Activating Token Index: 119

Text #5

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3405. Min Act: -0.0000

Data Index: 967216 (The Pile)

Max Activating Token Index: 827

Text #6

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3446. Min Act: -0.0000

Data Index: 1258834 (The Pile)

Max Activating Token Index: 32

Text #7

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3280. Min Act: -0.0000

Data Index: 1670904 (The Pile)

Max Activating Token Index: 949

Text #8

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3422. Min Act: -0.0000

Data Index: 1274536 (The Pile)

Max Activating Token Index: 756

Text #9

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3213. Min Act: -0.0000

Data Index: 203422 (The Pile)

Max Activating Token Index: 362

Text #10

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3348. Min Act: -0.0000

Data Index: 1804961 (The Pile)

Max Activating Token Index: 729

Text #11

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.2929. Min Act: -0.0000

Data Index: 138885 (The Pile)

Max Activating Token Index: 791

Text #12

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1235912 (The Pile)

Max Activating Token Index: 463

Text #13

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3094. Min Act: -0.0000

Data Index: 59840 (The Pile)

Max Activating Token Index: 485

Text #14

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3033. Min Act: -0.0000

Data Index: 760999 (The Pile)

Max Activating Token Index: 1017

Text #15

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.2979. Min Act: -0.0000

Data Index: 1467734 (The Pile)

Max Activating Token Index: 228

Text #16

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3078. Min Act: -0.0000

Data Index: 907574 (The Pile)

Max Activating Token Index: 816

Text #17

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3022. Min Act: -0.0000

Data Index: 1115788 (The Pile)

Max Activating Token Index: 567

Text #18

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3098. Min Act: -0.0000

Data Index: 853190 (The Pile)

Max Activating Token Index: 271

Text #19

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3161. Min Act: -0.0000

Data Index: 1480387 (The Pile)

Max Activating Token Index: 969