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

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

Neuron 3046 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0507. Min Range: -2.0507

Max Act: 1.9173. Min Act: -0.0000

Data Index: 983252 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 2.0507. Min Range: -2.0507

Max Act: 2.0507. Min Act: -0.0000

Data Index: 850567 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 2.0507. Min Range: -2.0507

Max Act: 1.9094. Min Act: -0.0000

Data Index: 136330 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 2.0507. Min Range: -2.0507

Max Act: 1.7257. Min Act: -0.0000

Data Index: 1416416 (Python Code)

Max Activating Token Index: 65

Text #4

Max Range: 2.0507. Min Range: -2.0507

Max Act: 1.7615. Min Act: -0.0000

Data Index: 1611999 (Python Code)

Max Activating Token Index: 360

Text #5

Max Range: 2.0507. Min Range: -2.0507

Max Act: 1.7213. Min Act: -0.0000

Data Index: 1406709 (Python Code)

Max Activating Token Index: 194

Text #6

Max Range: 2.0507. Min Range: -2.0507

Max Act: 1.7975. Min Act: -0.0000

Data Index: 1513898 (Python Code)

Max Activating Token Index: 371

Text #7

Max Range: 2.0507. Min Range: -2.0507

Max Act: 1.5817. Min Act: -0.0000

Data Index: 1633383 (Python Code)

Max Activating Token Index: 35

Text #8

Max Range: 2.0507. Min Range: -2.0507

Max Act: 1.9101. Min Act: -0.0000

Data Index: 1507732 (Python Code)

Max Activating Token Index: 797

Text #9

Max Range: 2.0507. Min Range: -2.0507

Max Act: 1.6139. Min Act: -0.0000

Data Index: 1610880 (Python Code)

Max Activating Token Index: 67

Text #10

Max Range: 2.0507. Min Range: -2.0507

Max Act: 1.5601. Min Act: -0.0000

Data Index: 1455613 (Python Code)

Max Activating Token Index: 827

Text #11

Max Range: 2.0507. Min Range: -2.0507

Max Act: 1.6174. Min Act: -0.0000

Data Index: 1594423 (Python Code)

Max Activating Token Index: 718

Text #12

Max Range: 2.0507. Min Range: -2.0507

Max Act: 1.3907. Min Act: -0.0000

Data Index: 890845 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 2.0507. Min Range: -2.0507

Max Act: 1.5159. Min Act: -0.0000

Data Index: 1104481 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 2.0507. Min Range: -2.0507

Max Act: 1.5632. Min Act: -0.0000

Data Index: 472728 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 2.0507. Min Range: -2.0507

Max Act: 1.4824. Min Act: -0.0000

Data Index: 1545268 (Python Code)

Max Activating Token Index: 782

Text #16

Max Range: 2.0507. Min Range: -2.0507

Max Act: 1.3680. Min Act: -0.0000

Data Index: 1533711 (Python Code)

Max Activating Token Index: 827

Text #17

Max Range: 2.0507. Min Range: -2.0507

Max Act: 1.4206. Min Act: -0.0000

Data Index: 1409843 (Python Code)

Max Activating Token Index: 35

Text #18

Max Range: 2.0507. Min Range: -2.0507

Max Act: 1.4939. Min Act: -0.0000

Data Index: 826104 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 2.0507. Min Range: -2.0507

Max Act: 1.3425. Min Act: -0.0000

Data Index: 491951 (C4 (Web Text))

Max Activating Token Index: 353