Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3045 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.9689. Min Act: -0.0001

Data Index: 147916 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.9011. Min Act: -0.0000

Data Index: 251476 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7757. Min Act: -0.0000

Data Index: 673809 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7584. Min Act: -0.0000

Data Index: 39713 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7950. Min Act: -0.0000

Data Index: 812727 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7519. Min Act: -0.0000

Data Index: 1129140 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7511. Min Act: -0.0000

Data Index: 1011312 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7532. Min Act: -0.0000

Data Index: 824270 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1071100 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7265. Min Act: -0.0000

Data Index: 1325043 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7427. Min Act: -0.0000

Data Index: 497958 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7107. Min Act: -0.0000

Data Index: 4805 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.6941. Min Act: -0.0001

Data Index: 889923 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.6781. Min Act: -0.0000

Data Index: 1117897 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7109. Min Act: -0.0000

Data Index: 195856 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.6675. Min Act: -0.0001

Data Index: 1176766 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.6993. Min Act: -0.0000

Data Index: 1196153 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.6885. Min Act: -0.0000

Data Index: 1179179 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1306613 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.6441. Min Act: -0.0000

Data Index: 321441 (C4 (Web Text))

Max Activating Token Index: 309