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

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

Neuron 1615 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: 0.2911. Min Range: -0.2911

Max Act: 0.2775. Min Act: -0.0000

Data Index: 526286 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2823. Min Act: -0.0000

Data Index: 498789 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2911. Min Act: -0.0000

Data Index: 139325 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2547. Min Act: -0.0000

Data Index: 793690 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2529. Min Act: -0.0000

Data Index: 348390 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2610. Min Act: -0.0000

Data Index: 408091 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2613. Min Act: -0.0000

Data Index: 396844 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2469. Min Act: -0.0000

Data Index: 646933 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1398740 (Python Code)

Max Activating Token Index: 56

Text #9

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2228. Min Act: -0.0000

Data Index: 104941 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2280. Min Act: -0.0000

Data Index: 1567518 (Python Code)

Max Activating Token Index: 235

Text #11

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2282. Min Act: -0.0000

Data Index: 1559048 (Python Code)

Max Activating Token Index: 274

Text #12

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2239. Min Act: -0.0000

Data Index: 1406256 (Python Code)

Max Activating Token Index: 78

Text #13

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2159. Min Act: -0.0000

Data Index: 1386434 (Python Code)

Max Activating Token Index: 397

Text #14

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2089. Min Act: -0.0000

Data Index: 1306351 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2132. Min Act: -0.0000

Data Index: 865609 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1559304 (Python Code)

Max Activating Token Index: 620

Text #17

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.1949. Min Act: -0.0000

Data Index: 1430052 (Python Code)

Max Activating Token Index: 167

Text #18

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1605397 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 0.2911. Min Range: -0.2911

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1500956 (Python Code)

Max Activating Token Index: 899