Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3022 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7396. Min Range: -1.7396

Max Act: 1.7396. Min Act: -0.0000

Data Index: 900912 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 1.7396. Min Range: -1.7396

Max Act: 1.7205. Min Act: -0.0000

Data Index: 1042244 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 1.7396. Min Range: -1.7396

Max Act: 1.5064. Min Act: -0.0000

Data Index: 100479 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 1.7396. Min Range: -1.7396

Max Act: 1.3870. Min Act: -0.0000

Data Index: 1146632 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 1.7396. Min Range: -1.7396

Max Act: 1.2767. Min Act: -0.0001

Data Index: 954040 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 1.7396. Min Range: -1.7396

Max Act: 1.2487. Min Act: -0.0001

Data Index: 326589 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 1.7396. Min Range: -1.7396

Max Act: 1.2985. Min Act: -0.0001

Data Index: 1319751 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 1.7396. Min Range: -1.7396

Max Act: 1.3218. Min Act: -0.0001

Data Index: 69240 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 1.7396. Min Range: -1.7396

Max Act: 1.3093. Min Act: -0.0001

Data Index: 1034443 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 1.7396. Min Range: -1.7396

Max Act: 1.2256. Min Act: -0.0001

Data Index: 1295982 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 1.7396. Min Range: -1.7396

Max Act: 1.2533. Min Act: -0.0001

Data Index: 447175 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 1.7396. Min Range: -1.7396

Max Act: 1.3275. Min Act: -0.0000

Data Index: 1308157 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 1.7396. Min Range: -1.7396

Max Act: 1.2887. Min Act: -0.0000

Data Index: 257675 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 1.7396. Min Range: -1.7396

Max Act: 1.2564. Min Act: -0.0001

Data Index: 976731 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 1.7396. Min Range: -1.7396

Max Act: 1.2115. Min Act: -0.0001

Data Index: 649282 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 1.7396. Min Range: -1.7396

Max Act: 1.1670. Min Act: -0.0001

Data Index: 1223235 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 1.7396. Min Range: -1.7396

Max Act: 1.1721. Min Act: -0.0001

Data Index: 25972 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 1.7396. Min Range: -1.7396

Max Act: 1.1557. Min Act: -0.0000

Data Index: 170119 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 1.7396. Min Range: -1.7396

Max Act: 1.1552. Min Act: -0.0000

Data Index: 1125569 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 1.7396. Min Range: -1.7396

Max Act: 1.1149. Min Act: -0.0000

Data Index: 734087 (C4 (Web Text))

Max Activating Token Index: 557