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

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

Neuron 228 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8980. Min Range: -7.8980

Max Act: 7.8980. Min Act: -0.0001

Data Index: 971367 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 7.8980. Min Range: -7.8980

Max Act: 7.5228. Min Act: -0.0001

Data Index: 1051978 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 7.8980. Min Range: -7.8980

Max Act: 7.3072. Min Act: -0.0001

Data Index: 270851 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 7.8980. Min Range: -7.8980

Max Act: 7.3608. Min Act: -0.0001

Data Index: 1064928 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 7.8980. Min Range: -7.8980

Max Act: 7.2876. Min Act: -0.0001

Data Index: 1109907 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 7.8980. Min Range: -7.8980

Max Act: 6.9608. Min Act: -0.0001

Data Index: 206611 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 7.8980. Min Range: -7.8980

Max Act: 7.0149. Min Act: -0.0001

Data Index: 795813 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 7.8980. Min Range: -7.8980

Max Act: 6.6052. Min Act: -0.0001

Data Index: 1102052 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 7.8980. Min Range: -7.8980

Max Act: 6.2628. Min Act: -0.0001

Data Index: 139329 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 7.8980. Min Range: -7.8980

Max Act: 6.1688. Min Act: -0.0001

Data Index: 1068990 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 7.8980. Min Range: -7.8980

Max Act: 6.7251. Min Act: -0.0001

Data Index: 330633 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 7.8980. Min Range: -7.8980

Max Act: 6.5012. Min Act: -0.0001

Data Index: 64132 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 7.8980. Min Range: -7.8980

Max Act: 6.6359. Min Act: -0.0001

Data Index: 214689 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 7.8980. Min Range: -7.8980

Max Act: 6.5851. Min Act: -0.0001

Data Index: 301904 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 7.8980. Min Range: -7.8980

Max Act: 6.4323. Min Act: -0.0001

Data Index: 137011 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 7.8980. Min Range: -7.8980

Max Act: 6.2612. Min Act: -0.0001

Data Index: 549394 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 7.8980. Min Range: -7.8980

Max Act: 6.5620. Min Act: -0.0001

Data Index: 98129 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 7.8980. Min Range: -7.8980

Max Act: 6.4728. Min Act: -0.0001

Data Index: 708873 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 7.8980. Min Range: -7.8980

Max Act: 6.4359. Min Act: -0.0001

Data Index: 1212710 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 7.8980. Min Range: -7.8980

Max Act: 5.9199. Min Act: -0.0001

Data Index: 803604 (C4 (Web Text))

Max Activating Token Index: 228