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

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

Neuron 5374 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.8825. Min Act: -0.0000

Data Index: 1488025 (Python Code)

Max Activating Token Index: 371

Text #1

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7656. Min Act: -0.0000

Data Index: 1545468 (Python Code)

Max Activating Token Index: 983

Text #2

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.8179. Min Act: -0.0000

Data Index: 132400 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.8067. Min Act: -0.0000

Data Index: 814980 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7392. Min Act: -0.0000

Data Index: 232545 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7996. Min Act: -0.0000

Data Index: 636813 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7480. Min Act: -0.0000

Data Index: 380905 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6996. Min Act: -0.0000

Data Index: 1364089 (Python Code)

Max Activating Token Index: 201

Text #8

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6980. Min Act: -0.0000

Data Index: 1189076 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1126684 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6307. Min Act: -0.0000

Data Index: 531045 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1610040 (Python Code)

Max Activating Token Index: 349

Text #12

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6450. Min Act: -0.0000

Data Index: 355019 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6674. Min Act: -0.0000

Data Index: 1618627 (Python Code)

Max Activating Token Index: 848

Text #14

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6244. Min Act: -0.0000

Data Index: 1480281 (Python Code)

Max Activating Token Index: 230

Text #15

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1285631 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6259. Min Act: -0.0000

Data Index: 1587927 (Python Code)

Max Activating Token Index: 344

Text #17

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6433. Min Act: -0.0000

Data Index: 1435191 (Python Code)

Max Activating Token Index: 555

Text #18

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6422. Min Act: -0.0000

Data Index: 1499001 (Python Code)

Max Activating Token Index: 795

Text #19

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6391. Min Act: -0.0000

Data Index: 988605 (C4 (Web Text))

Max Activating Token Index: 100