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

Dataset: The Pile

Neuron 2488 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: 0.1601. Min Range: -0.1601

Max Act: 0.1601. Min Act: -0.0000

Data Index: 1281415 (The Pile)

Max Activating Token Index: 746

Text #1

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1343. Min Act: -0.0000

Data Index: 1101420 (The Pile)

Max Activating Token Index: 182

Text #2

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1177. Min Act: -0.0000

Data Index: 356915 (The Pile)

Max Activating Token Index: 512

Text #3

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1711193 (The Pile)

Max Activating Token Index: 439

Text #4

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1051. Min Act: -0.0000

Data Index: 1581366 (The Pile)

Max Activating Token Index: 289

Text #5

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1051. Min Act: -0.0000

Data Index: 907059 (The Pile)

Max Activating Token Index: 798

Text #6

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1027. Min Act: -0.0000

Data Index: 354356 (The Pile)

Max Activating Token Index: 198

Text #7

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1801074 (The Pile)

Max Activating Token Index: 875

Text #8

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.0997. Min Act: -0.0000

Data Index: 1342520 (The Pile)

Max Activating Token Index: 220

Text #9

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.0976. Min Act: -0.0000

Data Index: 775676 (The Pile)

Max Activating Token Index: 796

Text #10

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.0928. Min Act: -0.0000

Data Index: 63655 (The Pile)

Max Activating Token Index: 663

Text #11

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1152206 (The Pile)

Max Activating Token Index: 597

Text #12

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1273200 (The Pile)

Max Activating Token Index: 682

Text #13

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.0899. Min Act: -0.0000

Data Index: 497771 (The Pile)

Max Activating Token Index: 963

Text #14

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.0944. Min Act: -0.0000

Data Index: 1906198 (The Pile)

Max Activating Token Index: 418

Text #15

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.0941. Min Act: -0.0000

Data Index: 539682 (The Pile)

Max Activating Token Index: 998

Text #16

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.0910. Min Act: -0.0000

Data Index: 1530045 (The Pile)

Max Activating Token Index: 133

Text #17

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.0923. Min Act: -0.0000

Data Index: 565225 (The Pile)

Max Activating Token Index: 555

Text #18

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.0861. Min Act: -0.0000

Data Index: 1864010 (The Pile)

Max Activating Token Index: 999

Text #19

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.0890. Min Act: -0.0000

Data Index: 692221 (The Pile)

Max Activating Token Index: 363