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

Dataset: The Pile

Neuron 3755 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.5466. Min Act: -0.0000

Data Index: 1198278 (The Pile)

Max Activating Token Index: 802

Text #1

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.5782. Min Act: 0.0000

Data Index: 788234 (The Pile)

Max Activating Token Index: 330

Text #2

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.5207. Min Act: -0.0000

Data Index: 499689 (The Pile)

Max Activating Token Index: 692

Text #3

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4915. Min Act: -0.0000

Data Index: 753134 (The Pile)

Max Activating Token Index: 695

Text #4

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1659663 (The Pile)

Max Activating Token Index: 462

Text #5

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1622918 (The Pile)

Max Activating Token Index: 771

Text #6

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1474981 (The Pile)

Max Activating Token Index: 906

Text #7

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4956. Min Act: -0.0000

Data Index: 385291 (The Pile)

Max Activating Token Index: 475

Text #8

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4916. Min Act: -0.0000

Data Index: 459090 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4443. Min Act: -0.0000

Data Index: 134256 (The Pile)

Max Activating Token Index: 148

Text #10

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4688. Min Act: -0.0000

Data Index: 877411 (The Pile)

Max Activating Token Index: 757

Text #11

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4629. Min Act: -0.0000

Data Index: 963941 (The Pile)

Max Activating Token Index: 690

Text #12

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4501. Min Act: -0.0000

Data Index: 1561153 (The Pile)

Max Activating Token Index: 234

Text #13

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4173. Min Act: 0.0000

Data Index: 1242598 (The Pile)

Max Activating Token Index: 736

Text #14

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4485. Min Act: -0.0000

Data Index: 909636 (The Pile)

Max Activating Token Index: 564

Text #15

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4356. Min Act: 0.0000

Data Index: 328983 (The Pile)

Max Activating Token Index: 98

Text #16

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4466. Min Act: -0.0000

Data Index: 1859679 (The Pile)

Max Activating Token Index: 837

Text #17

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4148. Min Act: -0.0000

Data Index: 1866090 (The Pile)

Max Activating Token Index: 1009

Text #18

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4339. Min Act: -0.0000

Data Index: 1145874 (The Pile)

Max Activating Token Index: 700

Text #19

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4133. Min Act: -0.0000

Data Index: 997987 (The Pile)

Max Activating Token Index: 107