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

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

Neuron 417 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4937. Min Range: -1.4937

Max Act: 1.4937. Min Act: -0.0000

Data Index: 1284417 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 1.4937. Min Range: -1.4937

Max Act: 1.3755. Min Act: -0.0000

Data Index: 1604743 (Python Code)

Max Activating Token Index: 208

Text #2

Max Range: 1.4937. Min Range: -1.4937

Max Act: 1.3167. Min Act: -0.0000

Data Index: 949151 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 1.4937. Min Range: -1.4937

Max Act: 1.2035. Min Act: -0.0000

Data Index: 1345706 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 1.4937. Min Range: -1.4937

Max Act: 1.1701. Min Act: -0.0000

Data Index: 1644984 (Python Code)

Max Activating Token Index: 159

Text #5

Max Range: 1.4937. Min Range: -1.4937

Max Act: 1.2350. Min Act: -0.0000

Data Index: 1421241 (Python Code)

Max Activating Token Index: 70

Text #6

Max Range: 1.4937. Min Range: -1.4937

Max Act: 1.1905. Min Act: -0.0000

Data Index: 832858 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 1.4937. Min Range: -1.4937

Max Act: 1.2528. Min Act: -0.0000

Data Index: 29819 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 1.4937. Min Range: -1.4937

Max Act: 1.1844. Min Act: -0.0000

Data Index: 1557649 (Python Code)

Max Activating Token Index: 126

Text #9

Max Range: 1.4937. Min Range: -1.4937

Max Act: 1.1439. Min Act: -0.0000

Data Index: 1550902 (Python Code)

Max Activating Token Index: 199

Text #10

Max Range: 1.4937. Min Range: -1.4937

Max Act: 1.1706. Min Act: 0.0000

Data Index: 896963 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 1.4937. Min Range: -1.4937

Max Act: 1.1585. Min Act: -0.0000

Data Index: 1385833 (Python Code)

Max Activating Token Index: 66

Text #12

Max Range: 1.4937. Min Range: -1.4937

Max Act: 1.0655. Min Act: -0.0000

Data Index: 1609702 (Python Code)

Max Activating Token Index: 70

Text #13

Max Range: 1.4937. Min Range: -1.4937

Max Act: 1.1253. Min Act: -0.0000

Data Index: 1601484 (Python Code)

Max Activating Token Index: 340

Text #14

Max Range: 1.4937. Min Range: -1.4937

Max Act: 1.1294. Min Act: -0.0000

Data Index: 824010 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 1.4937. Min Range: -1.4937

Max Act: 1.0530. Min Act: 0.0000

Data Index: 576570 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 1.4937. Min Range: -1.4937

Max Act: 1.0287. Min Act: -0.0000

Data Index: 1622882 (Python Code)

Max Activating Token Index: 142

Text #17

Max Range: 1.4937. Min Range: -1.4937

Max Act: 1.1182. Min Act: -0.0000

Data Index: 1559684 (Python Code)

Max Activating Token Index: 661

Text #18

Max Range: 1.4937. Min Range: -1.4937

Max Act: 1.0133. Min Act: -0.0000

Data Index: 429484 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 1.4937. Min Range: -1.4937

Max Act: 1.0464. Min Act: -0.0000

Data Index: 787860 (C4 (Web Text))

Max Activating Token Index: 104