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

Dataset: The Pile

Neuron 1940 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: 1.8070. Min Range: -1.8070

Max Act: 1.8022. Min Act: -0.0000

Data Index: 1257791 (The Pile)

Max Activating Token Index: 1001

Text #1

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.8070. Min Act: -0.0000

Data Index: 817394 (The Pile)

Max Activating Token Index: 960

Text #2

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.5967. Min Act: -0.0000

Data Index: 1590512 (The Pile)

Max Activating Token Index: 652

Text #3

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.7697. Min Act: -0.0000

Data Index: 972053 (The Pile)

Max Activating Token Index: 121

Text #4

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.5722. Min Act: -0.0000

Data Index: 224215 (The Pile)

Max Activating Token Index: 350

Text #5

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.5708. Min Act: -0.0000

Data Index: 1232263 (The Pile)

Max Activating Token Index: 989

Text #6

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.5624. Min Act: -0.0000

Data Index: 1652198 (The Pile)

Max Activating Token Index: 338

Text #7

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.4841. Min Act: -0.0000

Data Index: 1611542 (The Pile)

Max Activating Token Index: 227

Text #8

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.4377. Min Act: 0.0000

Data Index: 817638 (The Pile)

Max Activating Token Index: 78

Text #9

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.4096. Min Act: -0.0000

Data Index: 287297 (The Pile)

Max Activating Token Index: 410

Text #10

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.3899. Min Act: -0.0000

Data Index: 1062793 (The Pile)

Max Activating Token Index: 1000

Text #11

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.3828. Min Act: 0.0000

Data Index: 304456 (The Pile)

Max Activating Token Index: 427

Text #12

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.4033. Min Act: 0.0000

Data Index: 1136892 (The Pile)

Max Activating Token Index: 299

Text #13

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.2636. Min Act: -0.0000

Data Index: 1786912 (The Pile)

Max Activating Token Index: 877

Text #14

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.3620. Min Act: 0.0000

Data Index: 219063 (The Pile)

Max Activating Token Index: 429

Text #15

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.1898. Min Act: -0.0000

Data Index: 803743 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.1306. Min Act: -0.0000

Data Index: 575427 (The Pile)

Max Activating Token Index: 763

Text #17

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.2160. Min Act: -0.0000

Data Index: 1951112 (The Pile)

Max Activating Token Index: 970

Text #18

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.2031. Min Act: 0.0000

Data Index: 863438 (The Pile)

Max Activating Token Index: 997

Text #19

Max Range: 1.8070. Min Range: -1.8070

Max Act: 1.1881. Min Act: -0.0000

Data Index: 76081 (The Pile)

Max Activating Token Index: 57