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

Dataset: The Pile

Neuron 3253 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: 1.0757. Min Range: -1.0757

Max Act: 1.0757. Min Act: -0.0000

Data Index: 838287 (The Pile)

Max Activating Token Index: 568

Text #1

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.9709. Min Act: -0.0000

Data Index: 1523380 (The Pile)

Max Activating Token Index: 58

Text #2

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8656. Min Act: -0.0000

Data Index: 15560 (The Pile)

Max Activating Token Index: 906

Text #3

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8874. Min Act: -0.0000

Data Index: 130808 (The Pile)

Max Activating Token Index: 656

Text #4

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8317. Min Act: -0.0000

Data Index: 696049 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8737. Min Act: -0.0000

Data Index: 1904237 (The Pile)

Max Activating Token Index: 541

Text #6

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1570076 (The Pile)

Max Activating Token Index: 884

Text #7

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.9451. Min Act: -0.0000

Data Index: 1492473 (The Pile)

Max Activating Token Index: 401

Text #8

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.9123. Min Act: -0.0000

Data Index: 1291899 (The Pile)

Max Activating Token Index: 239

Text #9

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8577. Min Act: -0.0000

Data Index: 262 (The Pile)

Max Activating Token Index: 207

Text #10

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8910. Min Act: -0.0000

Data Index: 1287595 (The Pile)

Max Activating Token Index: 102

Text #11

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8330. Min Act: -0.0000

Data Index: 857767 (The Pile)

Max Activating Token Index: 108

Text #12

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8256. Min Act: -0.0000

Data Index: 1003199 (The Pile)

Max Activating Token Index: 823

Text #13

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8522. Min Act: -0.0000

Data Index: 106914 (The Pile)

Max Activating Token Index: 619

Text #14

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1618240 (The Pile)

Max Activating Token Index: 472

Text #15

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.7932. Min Act: -0.0000

Data Index: 1840440 (The Pile)

Max Activating Token Index: 152

Text #16

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8186. Min Act: -0.0000

Data Index: 1721234 (The Pile)

Max Activating Token Index: 32

Text #17

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8099. Min Act: -0.0000

Data Index: 49312 (The Pile)

Max Activating Token Index: 181

Text #18

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.8081. Min Act: -0.0000

Data Index: 599605 (The Pile)

Max Activating Token Index: 514

Text #19

Max Range: 1.0757. Min Range: -1.0757

Max Act: 0.7992. Min Act: -0.0000

Data Index: 1053949 (The Pile)

Max Activating Token Index: 599