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

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

Neuron 880 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4249. Min Range: -7.4249

Max Act: 7.4249. Min Act: -0.0000

Data Index: 1552798 (Python Code)

Max Activating Token Index: 927

Text #1

Max Range: 7.4249. Min Range: -7.4249

Max Act: 5.9820. Min Act: -0.0000

Data Index: 1374190 (Python Code)

Max Activating Token Index: 172

Text #2

Max Range: 7.4249. Min Range: -7.4249

Max Act: 6.2123. Min Act: -0.0000

Data Index: 1642648 (Python Code)

Max Activating Token Index: 847

Text #3

Max Range: 7.4249. Min Range: -7.4249

Max Act: 5.8998. Min Act: -0.0000

Data Index: 1537266 (Python Code)

Max Activating Token Index: 335

Text #4

Max Range: 7.4249. Min Range: -7.4249

Max Act: 5.8947. Min Act: -0.0000

Data Index: 1544675 (Python Code)

Max Activating Token Index: 55

Text #5

Max Range: 7.4249. Min Range: -7.4249

Max Act: 5.6529. Min Act: -0.0000

Data Index: 1525523 (Python Code)

Max Activating Token Index: 642

Text #6

Max Range: 7.4249. Min Range: -7.4249

Max Act: 5.7196. Min Act: -0.0000

Data Index: 1422776 (Python Code)

Max Activating Token Index: 63

Text #7

Max Range: 7.4249. Min Range: -7.4249

Max Act: 5.5753. Min Act: -0.0000

Data Index: 1431869 (Python Code)

Max Activating Token Index: 987

Text #8

Max Range: 7.4249. Min Range: -7.4249

Max Act: 5.6330. Min Act: -0.0000

Data Index: 1528963 (Python Code)

Max Activating Token Index: 199

Text #9

Max Range: 7.4249. Min Range: -7.4249

Max Act: 5.5301. Min Act: -0.0000

Data Index: 1530373 (Python Code)

Max Activating Token Index: 82

Text #10

Max Range: 7.4249. Min Range: -7.4249

Max Act: 5.2968. Min Act: -0.0000

Data Index: 1498256 (Python Code)

Max Activating Token Index: 59

Text #11

Max Range: 7.4249. Min Range: -7.4249

Max Act: 5.3095. Min Act: -0.0000

Data Index: 1506430 (Python Code)

Max Activating Token Index: 760

Text #12

Max Range: 7.4249. Min Range: -7.4249

Max Act: 5.2641. Min Act: -0.0000

Data Index: 1574425 (Python Code)

Max Activating Token Index: 499

Text #13

Max Range: 7.4249. Min Range: -7.4249

Max Act: 5.2666. Min Act: -0.0000

Data Index: 1536686 (Python Code)

Max Activating Token Index: 62

Text #14

Max Range: 7.4249. Min Range: -7.4249

Max Act: 5.2184. Min Act: -0.0000

Data Index: 1423657 (Python Code)

Max Activating Token Index: 253

Text #15

Max Range: 7.4249. Min Range: -7.4249

Max Act: 4.9922. Min Act: -0.0000

Data Index: 1463116 (Python Code)

Max Activating Token Index: 402

Text #16

Max Range: 7.4249. Min Range: -7.4249

Max Act: 4.9566. Min Act: -0.0000

Data Index: 1378747 (Python Code)

Max Activating Token Index: 534

Text #17

Max Range: 7.4249. Min Range: -7.4249

Max Act: 5.1239. Min Act: -0.0000

Data Index: 1637514 (Python Code)

Max Activating Token Index: 667

Text #18

Max Range: 7.4249. Min Range: -7.4249

Max Act: 4.6652. Min Act: -0.0000

Data Index: 1416519 (Python Code)

Max Activating Token Index: 80

Text #19

Max Range: 7.4249. Min Range: -7.4249

Max Act: 4.8150. Min Act: -0.0000

Data Index: 1376310 (Python Code)

Max Activating Token Index: 486