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

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

Neuron 2528 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: 4.3520. Min Range: -4.3520

Max Act: 4.3520. Min Act: -0.0000

Data Index: 1276050 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 4.3520. Min Range: -4.3520

Max Act: 3.7385. Min Act: -0.0000

Data Index: 224554 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 4.3520. Min Range: -4.3520

Max Act: 3.5593. Min Act: -0.0000

Data Index: 170983 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 4.3520. Min Range: -4.3520

Max Act: 3.8369. Min Act: -0.0000

Data Index: 538928 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 4.3520. Min Range: -4.3520

Max Act: 3.3556. Min Act: -0.0000

Data Index: 756715 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 4.3520. Min Range: -4.3520

Max Act: 3.3008. Min Act: -0.0000

Data Index: 659661 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 4.3520. Min Range: -4.3520

Max Act: 3.6365. Min Act: -0.0001

Data Index: 681686 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 4.3520. Min Range: -4.3520

Max Act: 3.2528. Min Act: -0.0000

Data Index: 197397 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 4.3520. Min Range: -4.3520

Max Act: 3.2204. Min Act: -0.0000

Data Index: 1221617 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 4.3520. Min Range: -4.3520

Max Act: 3.4648. Min Act: -0.0000

Data Index: 619274 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 4.3520. Min Range: -4.3520

Max Act: 3.3097. Min Act: -0.0000

Data Index: 865127 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 4.3520. Min Range: -4.3520

Max Act: 3.1167. Min Act: -0.0000

Data Index: 886155 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 4.3520. Min Range: -4.3520

Max Act: 2.8609. Min Act: -0.0000

Data Index: 754974 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 4.3520. Min Range: -4.3520

Max Act: 2.8464. Min Act: -0.0000

Data Index: 1202003 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 4.3520. Min Range: -4.3520

Max Act: 3.0018. Min Act: -0.0001

Data Index: 412401 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 4.3520. Min Range: -4.3520

Max Act: 2.9758. Min Act: -0.0001

Data Index: 360677 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 4.3520. Min Range: -4.3520

Max Act: 3.1099. Min Act: -0.0000

Data Index: 587237 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 4.3520. Min Range: -4.3520

Max Act: 2.6871. Min Act: -0.0000

Data Index: 1042745 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 4.3520. Min Range: -4.3520

Max Act: 3.1200. Min Act: -0.0000

Data Index: 244873 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 4.3520. Min Range: -4.3520

Max Act: 2.9788. Min Act: -0.0000

Data Index: 933127 (C4 (Web Text))

Max Activating Token Index: 144