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

Dataset: The Pile

Neuron 1471 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1430. Min Act: -0.0000

Data Index: 878272 (The Pile)

Max Activating Token Index: 41

Text #1

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1473. Min Act: -0.0000

Data Index: 965980 (The Pile)

Max Activating Token Index: 111

Text #2

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1088. Min Act: -0.0000

Data Index: 247196 (The Pile)

Max Activating Token Index: 244

Text #3

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1078. Min Act: -0.0000

Data Index: 1449093 (The Pile)

Max Activating Token Index: 409

Text #4

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0842. Min Act: -0.0000

Data Index: 990070 (The Pile)

Max Activating Token Index: 673

Text #5

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1091. Min Act: -0.0000

Data Index: 922761 (The Pile)

Max Activating Token Index: 776

Text #6

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0973. Min Act: -0.0000

Data Index: 1850428 (The Pile)

Max Activating Token Index: 767

Text #7

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0938. Min Act: -0.0000

Data Index: 1888778 (The Pile)

Max Activating Token Index: 302

Text #8

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0925. Min Act: -0.0000

Data Index: 782794 (The Pile)

Max Activating Token Index: 258

Text #9

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0939. Min Act: -0.0000

Data Index: 745261 (The Pile)

Max Activating Token Index: 575

Text #10

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0943. Min Act: -0.0000

Data Index: 1362911 (The Pile)

Max Activating Token Index: 535

Text #11

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0896. Min Act: -0.0000

Data Index: 1935920 (The Pile)

Max Activating Token Index: 738

Text #12

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0901. Min Act: -0.0000

Data Index: 295181 (The Pile)

Max Activating Token Index: 289

Text #13

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0850. Min Act: -0.0000

Data Index: 749280 (The Pile)

Max Activating Token Index: 651

Text #14

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0944. Min Act: -0.0000

Data Index: 1991957 (The Pile)

Max Activating Token Index: 578

Text #15

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0871. Min Act: -0.0000

Data Index: 401691 (The Pile)

Max Activating Token Index: 146

Text #16

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0806. Min Act: -0.0000

Data Index: 1166740 (The Pile)

Max Activating Token Index: 615

Text #17

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0931. Min Act: -0.0000

Data Index: 1780315 (The Pile)

Max Activating Token Index: 135

Text #18

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1388641 (The Pile)

Max Activating Token Index: 87

Text #19

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0887. Min Act: -0.0000

Data Index: 1660874 (The Pile)

Max Activating Token Index: 686