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

Dataset: The Pile

Neuron 2871 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: 0.5755. Min Range: -0.5755

Max Act: 0.5755. Min Act: -0.0000

Data Index: 58244 (The Pile)

Max Activating Token Index: 644

Text #1

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.3440. Min Act: -0.0000

Data Index: 1577983 (The Pile)

Max Activating Token Index: 860

Text #2

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.3503. Min Act: -0.0000

Data Index: 947143 (The Pile)

Max Activating Token Index: 479

Text #3

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.3511. Min Act: -0.0000

Data Index: 688983 (The Pile)

Max Activating Token Index: 148

Text #4

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.3623. Min Act: -0.0000

Data Index: 1931174 (The Pile)

Max Activating Token Index: 534

Text #5

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.3447. Min Act: -0.0000

Data Index: 583433 (The Pile)

Max Activating Token Index: 841

Text #6

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.3388. Min Act: -0.0000

Data Index: 776978 (The Pile)

Max Activating Token Index: 409

Text #7

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.3383. Min Act: -0.0000

Data Index: 41065 (The Pile)

Max Activating Token Index: 350

Text #8

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.3338. Min Act: -0.0000

Data Index: 512288 (The Pile)

Max Activating Token Index: 442

Text #9

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.3329. Min Act: -0.0000

Data Index: 90609 (The Pile)

Max Activating Token Index: 727

Text #10

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.3271. Min Act: -0.0000

Data Index: 155235 (The Pile)

Max Activating Token Index: 356

Text #11

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1384850 (The Pile)

Max Activating Token Index: 154

Text #12

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.3078. Min Act: -0.0000

Data Index: 1509663 (The Pile)

Max Activating Token Index: 746

Text #13

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.2907. Min Act: -0.0000

Data Index: 1901404 (The Pile)

Max Activating Token Index: 944

Text #14

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1235290 (The Pile)

Max Activating Token Index: 70

Text #15

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.3170. Min Act: -0.0000

Data Index: 1105033 (The Pile)

Max Activating Token Index: 54

Text #16

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.3147. Min Act: -0.0000

Data Index: 1515527 (The Pile)

Max Activating Token Index: 317

Text #17

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.3245. Min Act: -0.0000

Data Index: 1388183 (The Pile)

Max Activating Token Index: 863

Text #18

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.3017. Min Act: -0.0000

Data Index: 1076173 (The Pile)

Max Activating Token Index: 388

Text #19

Max Range: 0.5755. Min Range: -0.5755

Max Act: 0.3103. Min Act: -0.0000

Data Index: 819628 (The Pile)

Max Activating Token Index: 429