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

Dataset: The Pile

Neuron 1134 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: 0.5554. Min Range: -0.5554

Max Act: 0.5319. Min Act: -0.0000

Data Index: 1140653 (The Pile)

Max Activating Token Index: 160

Text #1

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.5554. Min Act: -0.0000

Data Index: 880951 (The Pile)

Max Activating Token Index: 713

Text #2

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.5395. Min Act: -0.0000

Data Index: 868324 (The Pile)

Max Activating Token Index: 89

Text #3

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1222974 (The Pile)

Max Activating Token Index: 203

Text #4

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.4839. Min Act: -0.0000

Data Index: 60424 (The Pile)

Max Activating Token Index: 601

Text #5

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.4302. Min Act: -0.0000

Data Index: 434600 (The Pile)

Max Activating Token Index: 412

Text #6

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.4027. Min Act: -0.0000

Data Index: 959020 (The Pile)

Max Activating Token Index: 309

Text #7

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.4045. Min Act: -0.0000

Data Index: 94566 (The Pile)

Max Activating Token Index: 539

Text #8

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3613. Min Act: -0.0000

Data Index: 954336 (The Pile)

Max Activating Token Index: 794

Text #9

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3857. Min Act: -0.0000

Data Index: 1926861 (The Pile)

Max Activating Token Index: 1001

Text #10

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3924. Min Act: -0.0000

Data Index: 815781 (The Pile)

Max Activating Token Index: 445

Text #11

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3847. Min Act: -0.0000

Data Index: 165381 (The Pile)

Max Activating Token Index: 438

Text #12

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3805. Min Act: -0.0000

Data Index: 330251 (The Pile)

Max Activating Token Index: 334

Text #13

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3783. Min Act: -0.0000

Data Index: 744969 (The Pile)

Max Activating Token Index: 979

Text #14

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3946. Min Act: -0.0000

Data Index: 1034596 (The Pile)

Max Activating Token Index: 489

Text #15

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3705. Min Act: -0.0000

Data Index: 1340781 (The Pile)

Max Activating Token Index: 347

Text #16

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3991. Min Act: -0.0000

Data Index: 1271489 (The Pile)

Max Activating Token Index: 288

Text #17

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.4107. Min Act: -0.0000

Data Index: 1972556 (The Pile)

Max Activating Token Index: 801

Text #18

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3866. Min Act: -0.0000

Data Index: 13199 (The Pile)

Max Activating Token Index: 776

Text #19

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3652. Min Act: -0.0000

Data Index: 570061 (The Pile)

Max Activating Token Index: 424