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

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

Neuron 2475 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: 2.5038. Min Range: -2.5038

Max Act: 2.5038. Min Act: -0.0000

Data Index: 1634277 (Python Code)

Max Activating Token Index: 487

Text #1

Max Range: 2.5038. Min Range: -2.5038

Max Act: 2.4845. Min Act: -0.0000

Data Index: 1425012 (Python Code)

Max Activating Token Index: 615

Text #2

Max Range: 2.5038. Min Range: -2.5038

Max Act: 2.4300. Min Act: -0.0000

Data Index: 1433813 (Python Code)

Max Activating Token Index: 346

Text #3

Max Range: 2.5038. Min Range: -2.5038

Max Act: 2.2705. Min Act: -0.0000

Data Index: 1495939 (Python Code)

Max Activating Token Index: 684

Text #4

Max Range: 2.5038. Min Range: -2.5038

Max Act: 2.1822. Min Act: -0.0000

Data Index: 1379004 (Python Code)

Max Activating Token Index: 571

Text #5

Max Range: 2.5038. Min Range: -2.5038

Max Act: 2.3912. Min Act: -0.0000

Data Index: 1439649 (Python Code)

Max Activating Token Index: 385

Text #6

Max Range: 2.5038. Min Range: -2.5038

Max Act: 2.1432. Min Act: -0.0000

Data Index: 1423574 (Python Code)

Max Activating Token Index: 932

Text #7

Max Range: 2.5038. Min Range: -2.5038

Max Act: 2.2220. Min Act: -0.0000

Data Index: 1410276 (Python Code)

Max Activating Token Index: 671

Text #8

Max Range: 2.5038. Min Range: -2.5038

Max Act: 2.1494. Min Act: -0.0000

Data Index: 1568958 (Python Code)

Max Activating Token Index: 260

Text #9

Max Range: 2.5038. Min Range: -2.5038

Max Act: 2.0417. Min Act: -0.0000

Data Index: 1638530 (Python Code)

Max Activating Token Index: 263

Text #10

Max Range: 2.5038. Min Range: -2.5038

Max Act: 2.0269. Min Act: -0.0000

Data Index: 1634942 (Python Code)

Max Activating Token Index: 320

Text #11

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.9662. Min Act: -0.0000

Data Index: 1581499 (Python Code)

Max Activating Token Index: 133

Text #12

Max Range: 2.5038. Min Range: -2.5038

Max Act: 2.0626. Min Act: -0.0000

Data Index: 1604065 (Python Code)

Max Activating Token Index: 453

Text #13

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.8750. Min Act: -0.0000

Data Index: 1574417 (Python Code)

Max Activating Token Index: 506

Text #14

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.8142. Min Act: -0.0000

Data Index: 1653916 (Python Code)

Max Activating Token Index: 181

Text #15

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.9079. Min Act: -0.0000

Data Index: 1612523 (Python Code)

Max Activating Token Index: 337

Text #16

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.8453. Min Act: -0.0000

Data Index: 1407834 (Python Code)

Max Activating Token Index: 155

Text #17

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.7143. Min Act: -0.0000

Data Index: 1557045 (Python Code)

Max Activating Token Index: 223

Text #18

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.8531. Min Act: -0.0000

Data Index: 1644729 (Python Code)

Max Activating Token Index: 286

Text #19

Max Range: 2.5038. Min Range: -2.5038

Max Act: 1.8442. Min Act: -0.0000

Data Index: 1418093 (Python Code)

Max Activating Token Index: 630