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

Dataset: The Pile

Neuron 4842 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: 3.3410. Min Range: -3.3410

Max Act: 3.0978. Min Act: -0.0000

Data Index: 852278 (The Pile)

Max Activating Token Index: 379

Text #1

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.3410. Min Act: -0.0000

Data Index: 1387386 (The Pile)

Max Activating Token Index: 987

Text #2

Max Range: 3.3410. Min Range: -3.3410

Max Act: 2.9933. Min Act: -0.0000

Data Index: 1142569 (The Pile)

Max Activating Token Index: 997

Text #3

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.1854. Min Act: -0.0000

Data Index: 940541 (The Pile)

Max Activating Token Index: 367

Text #4

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.0098. Min Act: -0.0000

Data Index: 174236 (The Pile)

Max Activating Token Index: 520

Text #5

Max Range: 3.3410. Min Range: -3.3410

Max Act: 2.7148. Min Act: -0.0000

Data Index: 1430660 (The Pile)

Max Activating Token Index: 162

Text #6

Max Range: 3.3410. Min Range: -3.3410

Max Act: 2.8425. Min Act: -0.0000

Data Index: 1329231 (The Pile)

Max Activating Token Index: 343

Text #7

Max Range: 3.3410. Min Range: -3.3410

Max Act: 2.9077. Min Act: -0.0000

Data Index: 1732738 (The Pile)

Max Activating Token Index: 710

Text #8

Max Range: 3.3410. Min Range: -3.3410

Max Act: 2.7586. Min Act: -0.0000

Data Index: 634726 (The Pile)

Max Activating Token Index: 125

Text #9

Max Range: 3.3410. Min Range: -3.3410

Max Act: 2.8713. Min Act: -0.0000

Data Index: 1840936 (The Pile)

Max Activating Token Index: 625

Text #10

Max Range: 3.3410. Min Range: -3.3410

Max Act: 2.6500. Min Act: -0.0000

Data Index: 1818557 (The Pile)

Max Activating Token Index: 191

Text #11

Max Range: 3.3410. Min Range: -3.3410

Max Act: 2.9127. Min Act: -0.0000

Data Index: 1623344 (The Pile)

Max Activating Token Index: 867

Text #12

Max Range: 3.3410. Min Range: -3.3410

Max Act: 2.6450. Min Act: -0.0000

Data Index: 1593039 (The Pile)

Max Activating Token Index: 325

Text #13

Max Range: 3.3410. Min Range: -3.3410

Max Act: 2.6489. Min Act: -0.0000

Data Index: 1909261 (The Pile)

Max Activating Token Index: 9

Text #14

Max Range: 3.3410. Min Range: -3.3410

Max Act: 2.7492. Min Act: -0.0000

Data Index: 451273 (The Pile)

Max Activating Token Index: 197

Text #15

Max Range: 3.3410. Min Range: -3.3410

Max Act: 2.8756. Min Act: -0.0000

Data Index: 951548 (The Pile)

Max Activating Token Index: 125

Text #16

Max Range: 3.3410. Min Range: -3.3410

Max Act: 2.5914. Min Act: -0.0000

Data Index: 1411297 (The Pile)

Max Activating Token Index: 984

Text #17

Max Range: 3.3410. Min Range: -3.3410

Max Act: 2.5249. Min Act: -0.0000

Data Index: 1146680 (The Pile)

Max Activating Token Index: 569

Text #18

Max Range: 3.3410. Min Range: -3.3410

Max Act: 2.6335. Min Act: -0.0000

Data Index: 668571 (The Pile)

Max Activating Token Index: 575

Text #19

Max Range: 3.3410. Min Range: -3.3410

Max Act: 2.6461. Min Act: -0.0000

Data Index: 901486 (The Pile)

Max Activating Token Index: 973