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

Dataset: The Pile

Neuron 1770 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: 0.5108. Min Range: -0.5108

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1390282 (The Pile)

Max Activating Token Index: 253

Text #1

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1393878 (The Pile)

Max Activating Token Index: 238

Text #2

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1209849 (The Pile)

Max Activating Token Index: 749

Text #3

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1472154 (The Pile)

Max Activating Token Index: 446

Text #4

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1055748 (The Pile)

Max Activating Token Index: 399

Text #5

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4215. Min Act: -0.0000

Data Index: 366031 (The Pile)

Max Activating Token Index: 346

Text #6

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3956. Min Act: -0.0000

Data Index: 1568609 (The Pile)

Max Activating Token Index: 514

Text #7

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3915. Min Act: -0.0000

Data Index: 628364 (The Pile)

Max Activating Token Index: 816

Text #8

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3780. Min Act: -0.0000

Data Index: 1200316 (The Pile)

Max Activating Token Index: 227

Text #9

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3786. Min Act: -0.0000

Data Index: 322892 (The Pile)

Max Activating Token Index: 628

Text #10

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4002. Min Act: -0.0000

Data Index: 1366971 (The Pile)

Max Activating Token Index: 696

Text #11

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3927. Min Act: -0.0000

Data Index: 258435 (The Pile)

Max Activating Token Index: 395

Text #12

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3593. Min Act: -0.0000

Data Index: 834071 (The Pile)

Max Activating Token Index: 163

Text #13

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3880. Min Act: -0.0000

Data Index: 542125 (The Pile)

Max Activating Token Index: 64

Text #14

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3512. Min Act: -0.0000

Data Index: 1339269 (The Pile)

Max Activating Token Index: 492

Text #15

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3677. Min Act: -0.0000

Data Index: 818006 (The Pile)

Max Activating Token Index: 473

Text #16

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.4018. Min Act: -0.0000

Data Index: 1149537 (The Pile)

Max Activating Token Index: 470

Text #17

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3450. Min Act: -0.0000

Data Index: 1852850 (The Pile)

Max Activating Token Index: 667

Text #18

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3313. Min Act: -0.0000

Data Index: 305037 (The Pile)

Max Activating Token Index: 69

Text #19

Max Range: 0.5108. Min Range: -0.5108

Max Act: 0.3737. Min Act: -0.0000

Data Index: 312790 (The Pile)

Max Activating Token Index: 503