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

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

Neuron 104 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: 3.7050. Min Range: -3.7050

Max Act: 3.7050. Min Act: -0.0000

Data Index: 1459128 (Python Code)

Max Activating Token Index: 171

Text #1

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.4303. Min Act: -0.0000

Data Index: 244303 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.5534. Min Act: -0.0000

Data Index: 1642019 (Python Code)

Max Activating Token Index: 599

Text #3

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.5354. Min Act: -0.0000

Data Index: 1377023 (Python Code)

Max Activating Token Index: 715

Text #4

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.0965. Min Act: -0.0000

Data Index: 1417708 (Python Code)

Max Activating Token Index: 705

Text #5

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.2205. Min Act: -0.0000

Data Index: 1384076 (Python Code)

Max Activating Token Index: 299

Text #6

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.2262. Min Act: -0.0000

Data Index: 1252762 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.1176. Min Act: -0.0000

Data Index: 1641981 (Python Code)

Max Activating Token Index: 966

Text #8

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.0652. Min Act: -0.0000

Data Index: 1408919 (Python Code)

Max Activating Token Index: 180

Text #9

Max Range: 3.7050. Min Range: -3.7050

Max Act: 2.9254. Min Act: -0.0000

Data Index: 1055453 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.0113. Min Act: -0.0000

Data Index: 1416914 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 3.7050. Min Range: -3.7050

Max Act: 2.8643. Min Act: -0.0000

Data Index: 1482932 (Python Code)

Max Activating Token Index: 271

Text #12

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.0748. Min Act: -0.0000

Data Index: 1435153 (Python Code)

Max Activating Token Index: 1004

Text #13

Max Range: 3.7050. Min Range: -3.7050

Max Act: 2.5722. Min Act: -0.0000

Data Index: 518415 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 3.7050. Min Range: -3.7050

Max Act: 2.4341. Min Act: -0.0000

Data Index: 1615849 (Python Code)

Max Activating Token Index: 804

Text #15

Max Range: 3.7050. Min Range: -3.7050

Max Act: 2.5624. Min Act: -0.0000

Data Index: 1534399 (Python Code)

Max Activating Token Index: 724

Text #16

Max Range: 3.7050. Min Range: -3.7050

Max Act: 2.4515. Min Act: -0.0000

Data Index: 1447935 (Python Code)

Max Activating Token Index: 486

Text #17

Max Range: 3.7050. Min Range: -3.7050

Max Act: 2.5501. Min Act: -0.0000

Data Index: 1423999 (Python Code)

Max Activating Token Index: 897

Text #18

Max Range: 3.7050. Min Range: -3.7050

Max Act: 2.4835. Min Act: -0.0000

Data Index: 1526652 (Python Code)

Max Activating Token Index: 16

Text #19

Max Range: 3.7050. Min Range: -3.7050

Max Act: 2.4746. Min Act: -0.0000

Data Index: 1511204 (Python Code)

Max Activating Token Index: 449