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

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

Neuron 5201 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: 3.0904. Min Range: -3.0904

Max Act: 3.0904. Min Act: -0.0000

Data Index: 956421 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 3.0904. Min Range: -3.0904

Max Act: 2.8387. Min Act: -0.0000

Data Index: 941696 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 3.0904. Min Range: -3.0904

Max Act: 2.9781. Min Act: -0.0000

Data Index: 1271394 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 3.0904. Min Range: -3.0904

Max Act: 3.0176. Min Act: -0.0000

Data Index: 1397009 (Python Code)

Max Activating Token Index: 238

Text #4

Max Range: 3.0904. Min Range: -3.0904

Max Act: 2.6016. Min Act: -0.0000

Data Index: 1541052 (Python Code)

Max Activating Token Index: 207

Text #5

Max Range: 3.0904. Min Range: -3.0904

Max Act: 2.3948. Min Act: -0.0000

Data Index: 886686 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 3.0904. Min Range: -3.0904

Max Act: 2.3422. Min Act: -0.0000

Data Index: 1447000 (Python Code)

Max Activating Token Index: 898

Text #7

Max Range: 3.0904. Min Range: -3.0904

Max Act: 2.5761. Min Act: -0.0000

Data Index: 1389197 (Python Code)

Max Activating Token Index: 662

Text #8

Max Range: 3.0904. Min Range: -3.0904

Max Act: 2.3567. Min Act: -0.0000

Data Index: 1541969 (Python Code)

Max Activating Token Index: 499

Text #9

Max Range: 3.0904. Min Range: -3.0904

Max Act: 2.3311. Min Act: -0.0000

Data Index: 1624073 (Python Code)

Max Activating Token Index: 253

Text #10

Max Range: 3.0904. Min Range: -3.0904

Max Act: 2.2001. Min Act: -0.0000

Data Index: 1602675 (Python Code)

Max Activating Token Index: 231

Text #11

Max Range: 3.0904. Min Range: -3.0904

Max Act: 2.0567. Min Act: -0.0000

Data Index: 1573023 (Python Code)

Max Activating Token Index: 305

Text #12

Max Range: 3.0904. Min Range: -3.0904

Max Act: 2.1588. Min Act: -0.0000

Data Index: 1591756 (Python Code)

Max Activating Token Index: 489

Text #13

Max Range: 3.0904. Min Range: -3.0904

Max Act: 2.1409. Min Act: -0.0000

Data Index: 1360237 (Python Code)

Max Activating Token Index: 604

Text #14

Max Range: 3.0904. Min Range: -3.0904

Max Act: 2.2065. Min Act: -0.0000

Data Index: 1152608 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 3.0904. Min Range: -3.0904

Max Act: 2.2038. Min Act: -0.0000

Data Index: 233029 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 3.0904. Min Range: -3.0904

Max Act: 2.0597. Min Act: -0.0000

Data Index: 1520109 (Python Code)

Max Activating Token Index: 123

Text #17

Max Range: 3.0904. Min Range: -3.0904

Max Act: 2.1393. Min Act: -0.0000

Data Index: 1441723 (Python Code)

Max Activating Token Index: 617

Text #18

Max Range: 3.0904. Min Range: -3.0904

Max Act: 1.8883. Min Act: -0.0000

Data Index: 1509731 (Python Code)

Max Activating Token Index: 138

Text #19

Max Range: 3.0904. Min Range: -3.0904

Max Act: 2.1050. Min Act: -0.0000

Data Index: 1368458 (Python Code)

Max Activating Token Index: 123