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

Dataset: The Pile

Neuron 2841 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: 0.6080. Min Range: -0.6080

Max Act: 0.6080. Min Act: -0.0000

Data Index: 782029 (The Pile)

Max Activating Token Index: 622

Text #1

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.5774. Min Act: -0.0000

Data Index: 90177 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.4805. Min Act: -0.0000

Data Index: 369256 (The Pile)

Max Activating Token Index: 576

Text #3

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.4470. Min Act: -0.0000

Data Index: 886169 (The Pile)

Max Activating Token Index: 413

Text #4

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3741. Min Act: -0.0000

Data Index: 1408245 (The Pile)

Max Activating Token Index: 890

Text #5

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3598. Min Act: -0.0000

Data Index: 1519572 (The Pile)

Max Activating Token Index: 940

Text #6

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3633. Min Act: -0.0000

Data Index: 888980 (The Pile)

Max Activating Token Index: 745

Text #7

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3498. Min Act: -0.0000

Data Index: 788469 (The Pile)

Max Activating Token Index: 439

Text #8

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3367. Min Act: -0.0000

Data Index: 1183096 (The Pile)

Max Activating Token Index: 711

Text #9

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3138. Min Act: -0.0000

Data Index: 1404937 (The Pile)

Max Activating Token Index: 720

Text #10

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3352. Min Act: -0.0000

Data Index: 1156807 (The Pile)

Max Activating Token Index: 705

Text #11

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1489202 (The Pile)

Max Activating Token Index: 238

Text #12

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3263. Min Act: -0.0000

Data Index: 1810926 (The Pile)

Max Activating Token Index: 342

Text #13

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3091. Min Act: -0.0000

Data Index: 72090 (The Pile)

Max Activating Token Index: 80

Text #14

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3059. Min Act: -0.0000

Data Index: 11315 (The Pile)

Max Activating Token Index: 882

Text #15

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.2860. Min Act: -0.0000

Data Index: 232117 (The Pile)

Max Activating Token Index: 1022

Text #16

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.3007. Min Act: -0.0000

Data Index: 1208069 (The Pile)

Max Activating Token Index: 1013

Text #17

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.2748. Min Act: -0.0000

Data Index: 1424337 (The Pile)

Max Activating Token Index: 945

Text #18

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.2989. Min Act: -0.0000

Data Index: 15161 (The Pile)

Max Activating Token Index: 976

Text #19

Max Range: 0.6080. Min Range: -0.6080

Max Act: 0.2816. Min Act: -0.0000

Data Index: 343759 (The Pile)

Max Activating Token Index: 816