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

Dataset: The Pile

Neuron 2200 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.6990. Min Range: -3.6990

Max Act: 3.6990. Min Act: -0.0000

Data Index: 1626371 (The Pile)

Max Activating Token Index: 719

Text #1

Max Range: 3.6990. Min Range: -3.6990

Max Act: 2.9418. Min Act: -0.0000

Data Index: 1906386 (The Pile)

Max Activating Token Index: 806

Text #2

Max Range: 3.6990. Min Range: -3.6990

Max Act: 2.5648. Min Act: -0.0000

Data Index: 551490 (The Pile)

Max Activating Token Index: 925

Text #3

Max Range: 3.6990. Min Range: -3.6990

Max Act: 2.5011. Min Act: -0.0000

Data Index: 1679143 (The Pile)

Max Activating Token Index: 896

Text #4

Max Range: 3.6990. Min Range: -3.6990

Max Act: 2.3000. Min Act: -0.0000

Data Index: 302488 (The Pile)

Max Activating Token Index: 189

Text #5

Max Range: 3.6990. Min Range: -3.6990

Max Act: 2.3710. Min Act: -0.0000

Data Index: 1782315 (The Pile)

Max Activating Token Index: 311

Text #6

Max Range: 3.6990. Min Range: -3.6990

Max Act: 2.4352. Min Act: -0.0000

Data Index: 1596013 (The Pile)

Max Activating Token Index: 734

Text #7

Max Range: 3.6990. Min Range: -3.6990

Max Act: 2.0062. Min Act: -0.0000

Data Index: 1616955 (The Pile)

Max Activating Token Index: 668

Text #8

Max Range: 3.6990. Min Range: -3.6990

Max Act: 2.3578. Min Act: -0.0000

Data Index: 776167 (The Pile)

Max Activating Token Index: 326

Text #9

Max Range: 3.6990. Min Range: -3.6990

Max Act: 2.2393. Min Act: -0.0000

Data Index: 1274117 (The Pile)

Max Activating Token Index: 676

Text #10

Max Range: 3.6990. Min Range: -3.6990

Max Act: 2.2240. Min Act: -0.0000

Data Index: 360476 (The Pile)

Max Activating Token Index: 362

Text #11

Max Range: 3.6990. Min Range: -3.6990

Max Act: 2.0942. Min Act: -0.0000

Data Index: 1100462 (The Pile)

Max Activating Token Index: 446

Text #12

Max Range: 3.6990. Min Range: -3.6990

Max Act: 2.1590. Min Act: -0.0000

Data Index: 202970 (The Pile)

Max Activating Token Index: 480

Text #13

Max Range: 3.6990. Min Range: -3.6990

Max Act: 2.1436. Min Act: -0.0000

Data Index: 1356899 (The Pile)

Max Activating Token Index: 102

Text #14

Max Range: 3.6990. Min Range: -3.6990

Max Act: 2.2054. Min Act: -0.0000

Data Index: 986895 (The Pile)

Max Activating Token Index: 670

Text #15

Max Range: 3.6990. Min Range: -3.6990

Max Act: 2.0974. Min Act: -0.0000

Data Index: 48883 (The Pile)

Max Activating Token Index: 552

Text #16

Max Range: 3.6990. Min Range: -3.6990

Max Act: 1.9695. Min Act: -0.0000

Data Index: 1215946 (The Pile)

Max Activating Token Index: 362

Text #17

Max Range: 3.6990. Min Range: -3.6990

Max Act: 2.0787. Min Act: -0.0000

Data Index: 154551 (The Pile)

Max Activating Token Index: 542

Text #18

Max Range: 3.6990. Min Range: -3.6990

Max Act: 2.0745. Min Act: -0.0000

Data Index: 791593 (The Pile)

Max Activating Token Index: 124

Text #19

Max Range: 3.6990. Min Range: -3.6990

Max Act: 2.0552. Min Act: -0.0000

Data Index: 114072 (The Pile)

Max Activating Token Index: 504