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

Dataset: The Pile

Neuron 436 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: 1.7168. Min Range: -1.7168

Max Act: 1.7168. Min Act: -0.0000

Data Index: 1483304 (The Pile)

Max Activating Token Index: 441

Text #1

Max Range: 1.7168. Min Range: -1.7168

Max Act: 1.5913. Min Act: -0.0000

Data Index: 493341 (The Pile)

Max Activating Token Index: 760

Text #2

Max Range: 1.7168. Min Range: -1.7168

Max Act: 1.4742. Min Act: -0.0000

Data Index: 1382689 (The Pile)

Max Activating Token Index: 1008

Text #3

Max Range: 1.7168. Min Range: -1.7168

Max Act: 1.6301. Min Act: -0.0000

Data Index: 126401 (The Pile)

Max Activating Token Index: 765

Text #4

Max Range: 1.7168. Min Range: -1.7168

Max Act: 1.4217. Min Act: -0.0000

Data Index: 1737524 (The Pile)

Max Activating Token Index: 338

Text #5

Max Range: 1.7168. Min Range: -1.7168

Max Act: 1.4127. Min Act: -0.0000

Data Index: 173182 (The Pile)

Max Activating Token Index: 921

Text #6

Max Range: 1.7168. Min Range: -1.7168

Max Act: 1.4203. Min Act: -0.0000

Data Index: 102591 (The Pile)

Max Activating Token Index: 213

Text #7

Max Range: 1.7168. Min Range: -1.7168

Max Act: 1.3057. Min Act: -0.0000

Data Index: 1668208 (The Pile)

Max Activating Token Index: 962

Text #8

Max Range: 1.7168. Min Range: -1.7168

Max Act: 1.4618. Min Act: -0.0000

Data Index: 168870 (The Pile)

Max Activating Token Index: 36

Text #9

Max Range: 1.7168. Min Range: -1.7168

Max Act: 1.4167. Min Act: -0.0000

Data Index: 923183 (The Pile)

Max Activating Token Index: 130

Text #10

Max Range: 1.7168. Min Range: -1.7168

Max Act: 1.3816. Min Act: -0.0000

Data Index: 623284 (The Pile)

Max Activating Token Index: 387

Text #11

Max Range: 1.7168. Min Range: -1.7168

Max Act: 1.2985. Min Act: -0.0000

Data Index: 1435825 (The Pile)

Max Activating Token Index: 767

Text #12

Max Range: 1.7168. Min Range: -1.7168

Max Act: 1.3687. Min Act: -0.0000

Data Index: 1383670 (The Pile)

Max Activating Token Index: 824

Text #13

Max Range: 1.7168. Min Range: -1.7168

Max Act: 1.4057. Min Act: -0.0000

Data Index: 932628 (The Pile)

Max Activating Token Index: 878

Text #14

Max Range: 1.7168. Min Range: -1.7168

Max Act: 1.4650. Min Act: -0.0000

Data Index: 1518391 (The Pile)

Max Activating Token Index: 979

Text #15

Max Range: 1.7168. Min Range: -1.7168

Max Act: 1.3964. Min Act: -0.0000

Data Index: 782938 (The Pile)

Max Activating Token Index: 632

Text #16

Max Range: 1.7168. Min Range: -1.7168

Max Act: 1.4001. Min Act: -0.0000

Data Index: 924803 (The Pile)

Max Activating Token Index: 978

Text #17

Max Range: 1.7168. Min Range: -1.7168

Max Act: 1.3805. Min Act: -0.0000

Data Index: 1727064 (The Pile)

Max Activating Token Index: 62

Text #18

Max Range: 1.7168. Min Range: -1.7168

Max Act: 1.3346. Min Act: -0.0000

Data Index: 357085 (The Pile)

Max Activating Token Index: 495

Text #19

Max Range: 1.7168. Min Range: -1.7168

Max Act: 1.4089. Min Act: -0.0000

Data Index: 1257171 (The Pile)

Max Activating Token Index: 915