Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1309 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 5.1362. Min Range: -5.1362

Max Act: 5.1362. Min Act: -0.1700

Data Index: 1502381 (Python Code)

Max Activating Token Index: 465

Text #1

Max Range: 5.1362. Min Range: -5.1362

Max Act: 5.1321. Min Act: -0.1700

Data Index: 1398874 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 5.1362. Min Range: -5.1362

Max Act: 5.0477. Min Act: -0.1700

Data Index: 1519353 (Python Code)

Max Activating Token Index: 790

Text #3

Max Range: 5.1362. Min Range: -5.1362

Max Act: 5.0204. Min Act: -0.1700

Data Index: 1477885 (Python Code)

Max Activating Token Index: 824

Text #4

Max Range: 5.1362. Min Range: -5.1362

Max Act: 5.0130. Min Act: -0.1700

Data Index: 1500972 (Python Code)

Max Activating Token Index: 400

Text #5

Max Range: 5.1362. Min Range: -5.1362

Max Act: 4.9894. Min Act: -0.1700

Data Index: 1412658 (Python Code)

Max Activating Token Index: 133

Text #6

Max Range: 5.1362. Min Range: -5.1362

Max Act: 4.9648. Min Act: -0.1700

Data Index: 1537130 (Python Code)

Max Activating Token Index: 644

Text #7

Max Range: 5.1362. Min Range: -5.1362

Max Act: 4.9468. Min Act: -0.1699

Data Index: 1360617 (Python Code)

Max Activating Token Index: 672

Text #8

Max Range: 5.1362. Min Range: -5.1362

Max Act: 4.9682. Min Act: -0.1700

Data Index: 1588141 (Python Code)

Max Activating Token Index: 534

Text #9

Max Range: 5.1362. Min Range: -5.1362

Max Act: 4.9382. Min Act: -0.1699

Data Index: 1465559 (Python Code)

Max Activating Token Index: 494

Text #10

Max Range: 5.1362. Min Range: -5.1362

Max Act: 4.9519. Min Act: -0.1700

Data Index: 1587702 (Python Code)

Max Activating Token Index: 401

Text #11

Max Range: 5.1362. Min Range: -5.1362

Max Act: 4.9423. Min Act: -0.1700

Data Index: 1579855 (Python Code)

Max Activating Token Index: 109

Text #12

Max Range: 5.1362. Min Range: -5.1362

Max Act: 4.9381. Min Act: -0.1700

Data Index: 1501696 (Python Code)

Max Activating Token Index: 369

Text #13

Max Range: 5.1362. Min Range: -5.1362

Max Act: 4.9393. Min Act: -0.1700

Data Index: 1556836 (Python Code)

Max Activating Token Index: 233

Text #14

Max Range: 5.1362. Min Range: -5.1362

Max Act: 4.8949. Min Act: -0.1700

Data Index: 1415468 (Python Code)

Max Activating Token Index: 1004

Text #15

Max Range: 5.1362. Min Range: -5.1362

Max Act: 4.8742. Min Act: -0.1700

Data Index: 1559958 (Python Code)

Max Activating Token Index: 979

Text #16

Max Range: 5.1362. Min Range: -5.1362

Max Act: 4.9378. Min Act: -0.1700

Data Index: 1390759 (Python Code)

Max Activating Token Index: 611

Text #17

Max Range: 5.1362. Min Range: -5.1362

Max Act: 4.9112. Min Act: -0.1700

Data Index: 1600426 (Python Code)

Max Activating Token Index: 165

Text #18

Max Range: 5.1362. Min Range: -5.1362

Max Act: 4.9150. Min Act: -0.1700

Data Index: 1408724 (Python Code)

Max Activating Token Index: 15

Text #19

Max Range: 5.1362. Min Range: -5.1362

Max Act: 4.9120. Min Act: -0.1700

Data Index: 1530063 (Python Code)

Max Activating Token Index: 9