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

Dataset: The Pile

Neuron 3538 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: 1.0862. Min Range: -1.0862

Max Act: 1.0862. Min Act: -0.0000

Data Index: 300210 (The Pile)

Max Activating Token Index: 795

Text #1

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1288949 (The Pile)

Max Activating Token Index: 154

Text #2

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.6825. Min Act: -0.0000

Data Index: 696082 (The Pile)

Max Activating Token Index: 773

Text #3

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.6785. Min Act: -0.0000

Data Index: 686176 (The Pile)

Max Activating Token Index: 947

Text #4

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.6706. Min Act: -0.0000

Data Index: 1701055 (The Pile)

Max Activating Token Index: 589

Text #5

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.6264. Min Act: -0.0000

Data Index: 177106 (The Pile)

Max Activating Token Index: 88

Text #6

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.6060. Min Act: -0.0000

Data Index: 479793 (The Pile)

Max Activating Token Index: 383

Text #7

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.6356. Min Act: -0.0000

Data Index: 29844 (The Pile)

Max Activating Token Index: 958

Text #8

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.6525. Min Act: -0.0000

Data Index: 921644 (The Pile)

Max Activating Token Index: 989

Text #9

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.6144. Min Act: -0.0000

Data Index: 1504989 (The Pile)

Max Activating Token Index: 753

Text #10

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.5895. Min Act: -0.0000

Data Index: 168369 (The Pile)

Max Activating Token Index: 453

Text #11

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.6061. Min Act: -0.0000

Data Index: 337196 (The Pile)

Max Activating Token Index: 995

Text #12

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1757403 (The Pile)

Max Activating Token Index: 469

Text #13

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.5810. Min Act: -0.0000

Data Index: 830851 (The Pile)

Max Activating Token Index: 971

Text #14

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1850525 (The Pile)

Max Activating Token Index: 228

Text #15

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.5654. Min Act: -0.0000

Data Index: 356935 (The Pile)

Max Activating Token Index: 819

Text #16

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1928941 (The Pile)

Max Activating Token Index: 825

Text #17

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.5460. Min Act: -0.0000

Data Index: 855114 (The Pile)

Max Activating Token Index: 151

Text #18

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.5442. Min Act: -0.0000

Data Index: 289440 (The Pile)

Max Activating Token Index: 849

Text #19

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.5924. Min Act: -0.0000

Data Index: 1393838 (The Pile)

Max Activating Token Index: 816