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

Dataset: The Pile

Neuron 2435 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: 0.3658. Min Range: -0.3658

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1529870 (The Pile)

Max Activating Token Index: 197

Text #1

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3658. Min Act: -0.0000

Data Index: 1137072 (The Pile)

Max Activating Token Index: 634

Text #2

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1942854 (The Pile)

Max Activating Token Index: 54

Text #3

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3294. Min Act: -0.0000

Data Index: 602753 (The Pile)

Max Activating Token Index: 555

Text #4

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3233. Min Act: -0.0000

Data Index: 1579459 (The Pile)

Max Activating Token Index: 670

Text #5

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3265. Min Act: -0.0000

Data Index: 648823 (The Pile)

Max Activating Token Index: 213

Text #6

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3277. Min Act: -0.0000

Data Index: 340565 (The Pile)

Max Activating Token Index: 621

Text #7

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1508846 (The Pile)

Max Activating Token Index: 539

Text #8

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3202. Min Act: -0.0000

Data Index: 1652324 (The Pile)

Max Activating Token Index: 32

Text #9

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3147. Min Act: -0.0000

Data Index: 146410 (The Pile)

Max Activating Token Index: 10

Text #10

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3004. Min Act: -0.0000

Data Index: 544322 (The Pile)

Max Activating Token Index: 570

Text #11

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3090. Min Act: -0.0000

Data Index: 1131952 (The Pile)

Max Activating Token Index: 121

Text #12

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.3060. Min Act: -0.0000

Data Index: 1281317 (The Pile)

Max Activating Token Index: 944

Text #13

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2805. Min Act: -0.0000

Data Index: 293050 (The Pile)

Max Activating Token Index: 13

Text #14

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2826. Min Act: -0.0000

Data Index: 655241 (The Pile)

Max Activating Token Index: 122

Text #15

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2812. Min Act: 0.0000

Data Index: 481120 (The Pile)

Max Activating Token Index: 661

Text #16

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2975. Min Act: -0.0000

Data Index: 1341990 (The Pile)

Max Activating Token Index: 950

Text #17

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2753. Min Act: 0.0000

Data Index: 875826 (The Pile)

Max Activating Token Index: 63

Text #18

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2792. Min Act: 0.0000

Data Index: 760884 (The Pile)

Max Activating Token Index: 631

Text #19

Max Range: 0.3658. Min Range: -0.3658

Max Act: 0.2742. Min Act: -0.0000

Data Index: 1114157 (The Pile)

Max Activating Token Index: 156