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

Dataset: The Pile

Neuron 4185 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: 1.1168. Min Range: -1.1168

Max Act: 1.0724. Min Act: -0.0000

Data Index: 1539765 (The Pile)

Max Activating Token Index: 51

Text #1

Max Range: 1.1168. Min Range: -1.1168

Max Act: 1.1168. Min Act: -0.0000

Data Index: 1061931 (The Pile)

Max Activating Token Index: 888

Text #2

Max Range: 1.1168. Min Range: -1.1168

Max Act: 0.9683. Min Act: -0.0000

Data Index: 1829090 (The Pile)

Max Activating Token Index: 59

Text #3

Max Range: 1.1168. Min Range: -1.1168

Max Act: 0.9514. Min Act: -0.0000

Data Index: 776596 (The Pile)

Max Activating Token Index: 168

Text #4

Max Range: 1.1168. Min Range: -1.1168

Max Act: 0.9458. Min Act: -0.0000

Data Index: 1510085 (The Pile)

Max Activating Token Index: 524

Text #5

Max Range: 1.1168. Min Range: -1.1168

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1203021 (The Pile)

Max Activating Token Index: 895

Text #6

Max Range: 1.1168. Min Range: -1.1168

Max Act: 0.8386. Min Act: -0.0000

Data Index: 1804798 (The Pile)

Max Activating Token Index: 746

Text #7

Max Range: 1.1168. Min Range: -1.1168

Max Act: 0.7193. Min Act: -0.0000

Data Index: 1013072 (The Pile)

Max Activating Token Index: 779

Text #8

Max Range: 1.1168. Min Range: -1.1168

Max Act: 0.7312. Min Act: -0.0000

Data Index: 1083130 (The Pile)

Max Activating Token Index: 275

Text #9

Max Range: 1.1168. Min Range: -1.1168

Max Act: 0.7602. Min Act: -0.0000

Data Index: 1221639 (The Pile)

Max Activating Token Index: 110

Text #10

Max Range: 1.1168. Min Range: -1.1168

Max Act: 0.7547. Min Act: -0.0000

Data Index: 982087 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 1.1168. Min Range: -1.1168

Max Act: 0.7814. Min Act: -0.0000

Data Index: 1569344 (The Pile)

Max Activating Token Index: 961

Text #12

Max Range: 1.1168. Min Range: -1.1168

Max Act: 0.7301. Min Act: -0.0000

Data Index: 107828 (The Pile)

Max Activating Token Index: 155

Text #13

Max Range: 1.1168. Min Range: -1.1168

Max Act: 0.7404. Min Act: -0.0000

Data Index: 1168901 (The Pile)

Max Activating Token Index: 644

Text #14

Max Range: 1.1168. Min Range: -1.1168

Max Act: 0.6902. Min Act: -0.0000

Data Index: 1407512 (The Pile)

Max Activating Token Index: 209

Text #15

Max Range: 1.1168. Min Range: -1.1168

Max Act: 0.7131. Min Act: -0.0000

Data Index: 1828750 (The Pile)

Max Activating Token Index: 961

Text #16

Max Range: 1.1168. Min Range: -1.1168

Max Act: 0.6833. Min Act: -0.0000

Data Index: 971252 (The Pile)

Max Activating Token Index: 338

Text #17

Max Range: 1.1168. Min Range: -1.1168

Max Act: 0.7042. Min Act: -0.0000

Data Index: 116274 (The Pile)

Max Activating Token Index: 346

Text #18

Max Range: 1.1168. Min Range: -1.1168

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1425813 (The Pile)

Max Activating Token Index: 758

Text #19

Max Range: 1.1168. Min Range: -1.1168

Max Act: 0.7107. Min Act: -0.0000

Data Index: 1996551 (The Pile)

Max Activating Token Index: 1008