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

Dataset: The Pile

Neuron 3447 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: 1.2474. Min Range: -1.2474

Max Act: 1.2474. Min Act: -0.0000

Data Index: 1932578 (The Pile)

Max Activating Token Index: 879

Text #1

Max Range: 1.2474. Min Range: -1.2474

Max Act: 1.1105. Min Act: -0.0000

Data Index: 1771387 (The Pile)

Max Activating Token Index: 832

Text #2

Max Range: 1.2474. Min Range: -1.2474

Max Act: 1.1372. Min Act: -0.0000

Data Index: 928750 (The Pile)

Max Activating Token Index: 147

Text #3

Max Range: 1.2474. Min Range: -1.2474

Max Act: 1.0164. Min Act: -0.0000

Data Index: 1643840 (The Pile)

Max Activating Token Index: 255

Text #4

Max Range: 1.2474. Min Range: -1.2474

Max Act: 1.0568. Min Act: -0.0000

Data Index: 673859 (The Pile)

Max Activating Token Index: 803

Text #5

Max Range: 1.2474. Min Range: -1.2474

Max Act: 0.9262. Min Act: -0.0000

Data Index: 1755128 (The Pile)

Max Activating Token Index: 341

Text #6

Max Range: 1.2474. Min Range: -1.2474

Max Act: 1.0351. Min Act: -0.0000

Data Index: 627765 (The Pile)

Max Activating Token Index: 255

Text #7

Max Range: 1.2474. Min Range: -1.2474

Max Act: 0.9835. Min Act: -0.0000

Data Index: 1488809 (The Pile)

Max Activating Token Index: 421

Text #8

Max Range: 1.2474. Min Range: -1.2474

Max Act: 0.8245. Min Act: -0.0000

Data Index: 932823 (The Pile)

Max Activating Token Index: 434

Text #9

Max Range: 1.2474. Min Range: -1.2474

Max Act: 0.8056. Min Act: -0.0000

Data Index: 54425 (The Pile)

Max Activating Token Index: 899

Text #10

Max Range: 1.2474. Min Range: -1.2474

Max Act: 0.8967. Min Act: -0.0000

Data Index: 143790 (The Pile)

Max Activating Token Index: 611

Text #11

Max Range: 1.2474. Min Range: -1.2474

Max Act: 1.0021. Min Act: -0.0000

Data Index: 819183 (The Pile)

Max Activating Token Index: 619

Text #12

Max Range: 1.2474. Min Range: -1.2474

Max Act: 0.9318. Min Act: -0.0000

Data Index: 1466931 (The Pile)

Max Activating Token Index: 136

Text #13

Max Range: 1.2474. Min Range: -1.2474

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1387508 (The Pile)

Max Activating Token Index: 1015

Text #14

Max Range: 1.2474. Min Range: -1.2474

Max Act: 1.0325. Min Act: -0.0000

Data Index: 1550735 (The Pile)

Max Activating Token Index: 595

Text #15

Max Range: 1.2474. Min Range: -1.2474

Max Act: 0.8566. Min Act: -0.0000

Data Index: 1881189 (The Pile)

Max Activating Token Index: 531

Text #16

Max Range: 1.2474. Min Range: -1.2474

Max Act: 0.8775. Min Act: 0.0000

Data Index: 1270023 (The Pile)

Max Activating Token Index: 852

Text #17

Max Range: 1.2474. Min Range: -1.2474

Max Act: 0.7877. Min Act: -0.0000

Data Index: 1043955 (The Pile)

Max Activating Token Index: 131

Text #18

Max Range: 1.2474. Min Range: -1.2474

Max Act: 0.9052. Min Act: -0.0000

Data Index: 172412 (The Pile)

Max Activating Token Index: 172

Text #19

Max Range: 1.2474. Min Range: -1.2474

Max Act: 0.8484. Min Act: -0.0000

Data Index: 1946536 (The Pile)

Max Activating Token Index: 320