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

Dataset: The Pile

Neuron 3527 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.9111. Min Act: -0.0000

Data Index: 1974114 (The Pile)

Max Activating Token Index: 995

Text #1

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.8952. Min Act: -0.0000

Data Index: 358090 (The Pile)

Max Activating Token Index: 626

Text #2

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7919. Min Act: -0.0000

Data Index: 1794492 (The Pile)

Max Activating Token Index: 990

Text #3

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.9072. Min Act: -0.0000

Data Index: 363011 (The Pile)

Max Activating Token Index: 848

Text #4

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.8155. Min Act: -0.0000

Data Index: 1071679 (The Pile)

Max Activating Token Index: 400

Text #5

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7775. Min Act: -0.0000

Data Index: 1430782 (The Pile)

Max Activating Token Index: 391

Text #6

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7256. Min Act: -0.0000

Data Index: 556836 (The Pile)

Max Activating Token Index: 463

Text #7

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1536249 (The Pile)

Max Activating Token Index: 947

Text #8

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.5729. Min Act: -0.0000

Data Index: 1978648 (The Pile)

Max Activating Token Index: 866

Text #9

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7276. Min Act: -0.0000

Data Index: 1131401 (The Pile)

Max Activating Token Index: 606

Text #10

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7037. Min Act: -0.0000

Data Index: 949947 (The Pile)

Max Activating Token Index: 51

Text #11

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6561. Min Act: -0.0000

Data Index: 1047044 (The Pile)

Max Activating Token Index: 960

Text #12

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.4677. Min Act: -0.0000

Data Index: 886565 (The Pile)

Max Activating Token Index: 705

Text #13

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6729. Min Act: -0.0000

Data Index: 820958 (The Pile)

Max Activating Token Index: 316

Text #14

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6304. Min Act: -0.0000

Data Index: 1263205 (The Pile)

Max Activating Token Index: 165

Text #15

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6824. Min Act: -0.0000

Data Index: 494004 (The Pile)

Max Activating Token Index: 249

Text #16

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6580. Min Act: -0.0000

Data Index: 1887001 (The Pile)

Max Activating Token Index: 123

Text #17

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6417. Min Act: -0.0000

Data Index: 255331 (The Pile)

Max Activating Token Index: 503

Text #18

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6224. Min Act: -0.0000

Data Index: 338868 (The Pile)

Max Activating Token Index: 285

Text #19

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1289923 (The Pile)

Max Activating Token Index: 724