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

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

Neuron 1325 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.4029. Min Act: -0.0001

Data Index: 1449233 (Python Code)

Max Activating Token Index: 833

Text #1

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.3528. Min Act: -0.0001

Data Index: 1637362 (Python Code)

Max Activating Token Index: 879

Text #2

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.2739. Min Act: -0.0001

Data Index: 1470604 (Python Code)

Max Activating Token Index: 233

Text #3

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.2555. Min Act: -0.0001

Data Index: 1430984 (Python Code)

Max Activating Token Index: 137

Text #4

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.2182. Min Act: -0.0001

Data Index: 1363412 (Python Code)

Max Activating Token Index: 739

Text #5

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0899. Min Act: -0.0001

Data Index: 1417340 (Python Code)

Max Activating Token Index: 821

Text #6

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.1900. Min Act: -0.0001

Data Index: 1623317 (Python Code)

Max Activating Token Index: 693

Text #7

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0921. Min Act: -0.0001

Data Index: 1544162 (Python Code)

Max Activating Token Index: 1016

Text #8

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.1384. Min Act: -0.0001

Data Index: 1383259 (Python Code)

Max Activating Token Index: 491

Text #9

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.1371. Min Act: -0.0001

Data Index: 1643181 (Python Code)

Max Activating Token Index: 669

Text #10

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.1525. Min Act: -0.0001

Data Index: 1381618 (Python Code)

Max Activating Token Index: 61

Text #11

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.1038. Min Act: -0.0001

Data Index: 1374320 (Python Code)

Max Activating Token Index: 892

Text #12

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0700. Min Act: -0.0001

Data Index: 1433428 (Python Code)

Max Activating Token Index: 17

Text #13

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0830. Min Act: -0.0001

Data Index: 1541357 (Python Code)

Max Activating Token Index: 396

Text #14

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0001. Min Act: -0.0001

Data Index: 1422091 (Python Code)

Max Activating Token Index: 470

Text #15

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0225. Min Act: -0.0001

Data Index: 1541352 (Python Code)

Max Activating Token Index: 175

Text #16

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0140. Min Act: -0.0001

Data Index: 1558098 (Python Code)

Max Activating Token Index: 219

Text #17

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0412. Min Act: -0.0001

Data Index: 1576835 (Python Code)

Max Activating Token Index: 737

Text #18

Max Range: 1.4029. Min Range: -1.4029

Max Act: 1.0498. Min Act: -0.0001

Data Index: 1405499 (Python Code)

Max Activating Token Index: 433

Text #19

Max Range: 1.4029. Min Range: -1.4029

Max Act: 0.9924. Min Act: -0.0001

Data Index: 1432763 (Python Code)

Max Activating Token Index: 781