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

Dataset: The Pile

Neuron 1742 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: 5.6150. Min Range: -5.6150

Max Act: 5.6150. Min Act: -0.0000

Data Index: 635118 (The Pile)

Max Activating Token Index: 51

Text #1

Max Range: 5.6150. Min Range: -5.6150

Max Act: 5.2334. Min Act: -0.0000

Data Index: 599081 (The Pile)

Max Activating Token Index: 78

Text #2

Max Range: 5.6150. Min Range: -5.6150

Max Act: 5.1616. Min Act: -0.0000

Data Index: 1654986 (The Pile)

Max Activating Token Index: 382

Text #3

Max Range: 5.6150. Min Range: -5.6150

Max Act: 5.1865. Min Act: -0.0000

Data Index: 1236995 (The Pile)

Max Activating Token Index: 146

Text #4

Max Range: 5.6150. Min Range: -5.6150

Max Act: 5.1701. Min Act: -0.0000

Data Index: 54738 (The Pile)

Max Activating Token Index: 70

Text #5

Max Range: 5.6150. Min Range: -5.6150

Max Act: 4.4281. Min Act: -0.0000

Data Index: 530725 (The Pile)

Max Activating Token Index: 67

Text #6

Max Range: 5.6150. Min Range: -5.6150

Max Act: 4.3998. Min Act: -0.0000

Data Index: 117379 (The Pile)

Max Activating Token Index: 37

Text #7

Max Range: 5.6150. Min Range: -5.6150

Max Act: 5.0041. Min Act: -0.0000

Data Index: 1089948 (The Pile)

Max Activating Token Index: 618

Text #8

Max Range: 5.6150. Min Range: -5.6150

Max Act: 4.2768. Min Act: -0.0000

Data Index: 142744 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 5.6150. Min Range: -5.6150

Max Act: 4.6362. Min Act: -0.0000

Data Index: 964734 (The Pile)

Max Activating Token Index: 146

Text #10

Max Range: 5.6150. Min Range: -5.6150

Max Act: 4.4828. Min Act: -0.0000

Data Index: 73946 (The Pile)

Max Activating Token Index: 375

Text #11

Max Range: 5.6150. Min Range: -5.6150

Max Act: 4.4387. Min Act: -0.0000

Data Index: 1312130 (The Pile)

Max Activating Token Index: 339

Text #12

Max Range: 5.6150. Min Range: -5.6150

Max Act: 5.4484. Min Act: -0.0000

Data Index: 108272 (The Pile)

Max Activating Token Index: 805

Text #13

Max Range: 5.6150. Min Range: -5.6150

Max Act: 4.3018. Min Act: -0.0000

Data Index: 1592347 (The Pile)

Max Activating Token Index: 414

Text #14

Max Range: 5.6150. Min Range: -5.6150

Max Act: 4.4480. Min Act: -0.0000

Data Index: 1226662 (The Pile)

Max Activating Token Index: 25

Text #15

Max Range: 5.6150. Min Range: -5.6150

Max Act: 4.3261. Min Act: -0.0000

Data Index: 796859 (The Pile)

Max Activating Token Index: 422

Text #16

Max Range: 5.6150. Min Range: -5.6150

Max Act: 3.9963. Min Act: -0.0000

Data Index: 1009102 (The Pile)

Max Activating Token Index: 292

Text #17

Max Range: 5.6150. Min Range: -5.6150

Max Act: 4.3150. Min Act: -0.0000

Data Index: 202756 (The Pile)

Max Activating Token Index: 102

Text #18

Max Range: 5.6150. Min Range: -5.6150

Max Act: 4.3101. Min Act: -0.0000

Data Index: 549535 (The Pile)

Max Activating Token Index: 290

Text #19

Max Range: 5.6150. Min Range: -5.6150

Max Act: 3.9949. Min Act: -0.0000

Data Index: 52895 (The Pile)

Max Activating Token Index: 746