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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2469 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1922. Min Range: -1.1922

Max Act: 1.1922. Min Act: -0.0000

Data Index: 1259183 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 1.1922. Min Range: -1.1922

Max Act: 1.0000. Min Act: -0.0000

Data Index: 1034886 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 1.1922. Min Range: -1.1922

Max Act: 0.9690. Min Act: -0.0000

Data Index: 834182 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 1.1922. Min Range: -1.1922

Max Act: 0.8345. Min Act: -0.0000

Data Index: 54570 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 1.1922. Min Range: -1.1922

Max Act: 0.8159. Min Act: -0.0000

Data Index: 1184061 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 1.1922. Min Range: -1.1922

Max Act: 0.7412. Min Act: -0.0000

Data Index: 1054439 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 1.1922. Min Range: -1.1922

Max Act: 0.7487. Min Act: -0.0000

Data Index: 649944 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 1.1922. Min Range: -1.1922

Max Act: 0.7218. Min Act: -0.0000

Data Index: 181088 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 1.1922. Min Range: -1.1922

Max Act: 0.7599. Min Act: -0.0000

Data Index: 57676 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 1.1922. Min Range: -1.1922

Max Act: 0.7708. Min Act: -0.0000

Data Index: 815498 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 1.1922. Min Range: -1.1922

Max Act: 0.7266. Min Act: -0.0000

Data Index: 247325 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 1.1922. Min Range: -1.1922

Max Act: 0.7122. Min Act: -0.0000

Data Index: 104153 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 1.1922. Min Range: -1.1922

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1240180 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 1.1922. Min Range: -1.1922

Max Act: 0.7334. Min Act: -0.0000

Data Index: 1125372 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 1.1922. Min Range: -1.1922

Max Act: 0.6952. Min Act: -0.0000

Data Index: 637139 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 1.1922. Min Range: -1.1922

Max Act: 0.7077. Min Act: -0.0000

Data Index: 353801 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 1.1922. Min Range: -1.1922

Max Act: 0.7299. Min Act: -0.0000

Data Index: 1276454 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 1.1922. Min Range: -1.1922

Max Act: 0.6620. Min Act: -0.0000

Data Index: 48291 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 1.1922. Min Range: -1.1922

Max Act: 0.6598. Min Act: -0.0000

Data Index: 971322 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 1.1922. Min Range: -1.1922

Max Act: 0.6975. Min Act: -0.0000

Data Index: 1082027 (C4 (Web Text))

Max Activating Token Index: 70