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

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

Neuron 4156 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.8068. Min Act: -0.0000

Data Index: 143204 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.7464. Min Act: -0.0000

Data Index: 544240 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1286701 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.7011. Min Act: -0.0000

Data Index: 1174107 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6280. Min Act: -0.0000

Data Index: 264148 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6867. Min Act: -0.0000

Data Index: 366234 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.7076. Min Act: -0.0000

Data Index: 110121 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6601. Min Act: -0.0000

Data Index: 338977 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6555. Min Act: -0.0000

Data Index: 281324 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6657. Min Act: -0.0000

Data Index: 747863 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6359. Min Act: -0.0000

Data Index: 456393 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6383. Min Act: -0.0000

Data Index: 129238 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6552. Min Act: -0.0000

Data Index: 267969 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6143. Min Act: -0.0000

Data Index: 339925 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6333. Min Act: -0.0000

Data Index: 356475 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6451. Min Act: -0.0000

Data Index: 563203 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1264962 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6793. Min Act: -0.0000

Data Index: 1103229 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6265. Min Act: -0.0000

Data Index: 571349 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 0.8068. Min Range: -0.8068

Max Act: 0.6012. Min Act: -0.0000

Data Index: 403310 (C4 (Web Text))

Max Activating Token Index: 437