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

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

Neuron 4010 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9747. Min Range: -1.9747

Max Act: 1.8343. Min Act: -0.0001

Data Index: 95016 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 1.9747. Min Range: -1.9747

Max Act: 1.9747. Min Act: -0.0001

Data Index: 125070 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 1.9747. Min Range: -1.9747

Max Act: 1.8563. Min Act: -0.0001

Data Index: 938071 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 1.9747. Min Range: -1.9747

Max Act: 1.6280. Min Act: -0.0001

Data Index: 929698 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 1.9747. Min Range: -1.9747

Max Act: 1.3042. Min Act: -0.0001

Data Index: 29562 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 1.9747. Min Range: -1.9747

Max Act: 1.1211. Min Act: -0.0001

Data Index: 1276015 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 1.9747. Min Range: -1.9747

Max Act: 1.2081. Min Act: -0.0001

Data Index: 755535 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 1.9747. Min Range: -1.9747

Max Act: 1.1186. Min Act: -0.0001

Data Index: 429978 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 1.9747. Min Range: -1.9747

Max Act: 1.1778. Min Act: -0.0001

Data Index: 1138114 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 1.9747. Min Range: -1.9747

Max Act: 1.1264. Min Act: -0.0001

Data Index: 35807 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 1.9747. Min Range: -1.9747

Max Act: 1.2443. Min Act: -0.0000

Data Index: 1232344 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 1.9747. Min Range: -1.9747

Max Act: 1.1163. Min Act: -0.0001

Data Index: 804009 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 1.9747. Min Range: -1.9747

Max Act: 1.0558. Min Act: -0.0001

Data Index: 247924 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 1.9747. Min Range: -1.9747

Max Act: 1.0095. Min Act: -0.0001

Data Index: 1089192 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 1.9747. Min Range: -1.9747

Max Act: 0.9802. Min Act: -0.0001

Data Index: 303623 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 1.9747. Min Range: -1.9747

Max Act: 0.9348. Min Act: -0.0001

Data Index: 1247403 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 1.9747. Min Range: -1.9747

Max Act: 0.9348. Min Act: -0.0001

Data Index: 237288 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 1.9747. Min Range: -1.9747

Max Act: 0.8125. Min Act: -0.0000

Data Index: 135692 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 1.9747. Min Range: -1.9747

Max Act: 0.9965. Min Act: -0.0001

Data Index: 254539 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 1.9747. Min Range: -1.9747

Max Act: 0.8838. Min Act: -0.0001

Data Index: 1247316 (C4 (Web Text))

Max Activating Token Index: 492