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

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

Neuron 5831 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.5346. Min Act: -0.0000

Data Index: 475508 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.5369. Min Act: -0.0000

Data Index: 1622585 (Python Code)

Max Activating Token Index: 451

Text #2

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.5104. Min Act: -0.0001

Data Index: 1611994 (Python Code)

Max Activating Token Index: 810

Text #3

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.5182. Min Act: -0.0000

Data Index: 1581405 (Python Code)

Max Activating Token Index: 186

Text #4

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4905. Min Act: -0.0000

Data Index: 372368 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.5053. Min Act: -0.0001

Data Index: 1467661 (Python Code)

Max Activating Token Index: 517

Text #6

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.5217. Min Act: -0.0001

Data Index: 1487874 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4668. Min Act: -0.0001

Data Index: 1435502 (Python Code)

Max Activating Token Index: 310

Text #8

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4929. Min Act: -0.0000

Data Index: 1612023 (Python Code)

Max Activating Token Index: 80

Text #9

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4880. Min Act: -0.0001

Data Index: 1522635 (Python Code)

Max Activating Token Index: 755

Text #10

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4870. Min Act: -0.0001

Data Index: 1478365 (Python Code)

Max Activating Token Index: 20

Text #11

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4791. Min Act: -0.0000

Data Index: 1616717 (Python Code)

Max Activating Token Index: 76

Text #12

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1582622 (Python Code)

Max Activating Token Index: 13

Text #13

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1586962 (Python Code)

Max Activating Token Index: 357

Text #14

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1516627 (Python Code)

Max Activating Token Index: 425

Text #15

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4532. Min Act: -0.0000

Data Index: 409194 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1614987 (Python Code)

Max Activating Token Index: 925

Text #17

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4571. Min Act: -0.0001

Data Index: 1389181 (Python Code)

Max Activating Token Index: 19

Text #18

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4610. Min Act: -0.0001

Data Index: 1623050 (Python Code)

Max Activating Token Index: 562

Text #19

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1508968 (Python Code)

Max Activating Token Index: 809