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

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

Neuron 3100 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: 1.2793. Min Range: -1.2793

Max Act: 1.2793. Min Act: -0.0000

Data Index: 568539 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.1179. Min Act: -0.0000

Data Index: 1413012 (Python Code)

Max Activating Token Index: 227

Text #2

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.0501. Min Act: -0.0000

Data Index: 1336250 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.9571. Min Act: -0.0000

Data Index: 137187 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8380. Min Act: -0.0000

Data Index: 385925 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.9065. Min Act: -0.0000

Data Index: 813540 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.9164. Min Act: -0.0000

Data Index: 1635491 (Python Code)

Max Activating Token Index: 130

Text #7

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.9061. Min Act: -0.0000

Data Index: 236063 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8592. Min Act: -0.0000

Data Index: 1565536 (Python Code)

Max Activating Token Index: 230

Text #9

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.9152. Min Act: -0.0000

Data Index: 1562990 (Python Code)

Max Activating Token Index: 308

Text #10

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8843. Min Act: -0.0000

Data Index: 916424 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8894. Min Act: -0.0000

Data Index: 1418008 (Python Code)

Max Activating Token Index: 94

Text #12

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.9073. Min Act: -0.0000

Data Index: 1484598 (Python Code)

Max Activating Token Index: 510

Text #13

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.9077. Min Act: -0.0000

Data Index: 292180 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8999. Min Act: -0.0000

Data Index: 796890 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1498212 (Python Code)

Max Activating Token Index: 120

Text #16

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.9253. Min Act: -0.0000

Data Index: 386812 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8574. Min Act: -0.0000

Data Index: 1099927 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8532. Min Act: -0.0000

Data Index: 1550508 (Python Code)

Max Activating Token Index: 118

Text #19

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8552. Min Act: -0.0000

Data Index: 1596870 (Python Code)

Max Activating Token Index: 540