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

Dataset: The Pile

Neuron 1622 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2469. Min Range: -3.2469

Max Act: 3.2469. Min Act: -0.0000

Data Index: 334513 (The Pile)

Max Activating Token Index: 709

Text #1

Max Range: 3.2469. Min Range: -3.2469

Max Act: 3.0977. Min Act: -0.0000

Data Index: 989290 (The Pile)

Max Activating Token Index: 254

Text #2

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.9303. Min Act: -0.0000

Data Index: 1222778 (The Pile)

Max Activating Token Index: 625

Text #3

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.9119. Min Act: -0.0000

Data Index: 601104 (The Pile)

Max Activating Token Index: 558

Text #4

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.9998. Min Act: -0.0000

Data Index: 412735 (The Pile)

Max Activating Token Index: 682

Text #5

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.9883. Min Act: -0.0000

Data Index: 471376 (The Pile)

Max Activating Token Index: 320

Text #6

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.9849. Min Act: -0.0000

Data Index: 553206 (The Pile)

Max Activating Token Index: 693

Text #7

Max Range: 3.2469. Min Range: -3.2469

Max Act: 3.2216. Min Act: -0.0000

Data Index: 1225123 (The Pile)

Max Activating Token Index: 881

Text #8

Max Range: 3.2469. Min Range: -3.2469

Max Act: 3.0217. Min Act: -0.0000

Data Index: 499827 (The Pile)

Max Activating Token Index: 526

Text #9

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.6957. Min Act: -0.0000

Data Index: 706197 (The Pile)

Max Activating Token Index: 674

Text #10

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.6866. Min Act: -0.0000

Data Index: 870464 (The Pile)

Max Activating Token Index: 522

Text #11

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.9032. Min Act: -0.0000

Data Index: 1202193 (The Pile)

Max Activating Token Index: 883

Text #12

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.5952. Min Act: -0.0000

Data Index: 1589424 (The Pile)

Max Activating Token Index: 308

Text #13

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.6635. Min Act: -0.0000

Data Index: 1611947 (The Pile)

Max Activating Token Index: 40

Text #14

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.5726. Min Act: -0.0000

Data Index: 161356 (The Pile)

Max Activating Token Index: 752

Text #15

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.5204. Min Act: -0.0000

Data Index: 594524 (The Pile)

Max Activating Token Index: 752

Text #16

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.6173. Min Act: -0.0000

Data Index: 1053430 (The Pile)

Max Activating Token Index: 593

Text #17

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.5847. Min Act: -0.0000

Data Index: 1887187 (The Pile)

Max Activating Token Index: 419

Text #18

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.7052. Min Act: -0.0000

Data Index: 700678 (The Pile)

Max Activating Token Index: 564

Text #19

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.3258. Min Act: -0.0000

Data Index: 1387440 (The Pile)

Max Activating Token Index: 677