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

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

Neuron 1505 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: 4.2508. Min Range: -4.2508

Max Act: 4.2508. Min Act: -0.1700

Data Index: 1365103 (Python Code)

Max Activating Token Index: 239

Text #1

Max Range: 4.2508. Min Range: -4.2508

Max Act: 4.2170. Min Act: -0.1700

Data Index: 1457562 (Python Code)

Max Activating Token Index: 441

Text #2

Max Range: 4.2508. Min Range: -4.2508

Max Act: 4.1860. Min Act: -0.1700

Data Index: 1637174 (Python Code)

Max Activating Token Index: 585

Text #3

Max Range: 4.2508. Min Range: -4.2508

Max Act: 4.1628. Min Act: -0.1700

Data Index: 1559836 (Python Code)

Max Activating Token Index: 150

Text #4

Max Range: 4.2508. Min Range: -4.2508

Max Act: 4.1239. Min Act: -0.1700

Data Index: 1388652 (Python Code)

Max Activating Token Index: 217

Text #5

Max Range: 4.2508. Min Range: -4.2508

Max Act: 4.1505. Min Act: -0.1700

Data Index: 1369152 (Python Code)

Max Activating Token Index: 260

Text #6

Max Range: 4.2508. Min Range: -4.2508

Max Act: 4.0980. Min Act: -0.1700

Data Index: 1636334 (Python Code)

Max Activating Token Index: 802

Text #7

Max Range: 4.2508. Min Range: -4.2508

Max Act: 4.0571. Min Act: -0.1700

Data Index: 1653217 (Python Code)

Max Activating Token Index: 827

Text #8

Max Range: 4.2508. Min Range: -4.2508

Max Act: 3.9525. Min Act: -0.1700

Data Index: 1537400 (Python Code)

Max Activating Token Index: 447

Text #9

Max Range: 4.2508. Min Range: -4.2508

Max Act: 3.9093. Min Act: -0.1700

Data Index: 14792 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 4.2508. Min Range: -4.2508

Max Act: 3.9198. Min Act: -0.1700

Data Index: 1602366 (Python Code)

Max Activating Token Index: 442

Text #11

Max Range: 4.2508. Min Range: -4.2508

Max Act: 3.8803. Min Act: -0.1700

Data Index: 1254364 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 4.2508. Min Range: -4.2508

Max Act: 3.8529. Min Act: -0.1700

Data Index: 1127521 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 4.2508. Min Range: -4.2508

Max Act: 3.8813. Min Act: -0.1700

Data Index: 49026 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 4.2508. Min Range: -4.2508

Max Act: 3.8430. Min Act: -0.1700

Data Index: 1467507 (Python Code)

Max Activating Token Index: 355

Text #15

Max Range: 4.2508. Min Range: -4.2508

Max Act: 3.8271. Min Act: -0.1700

Data Index: 229228 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 4.2508. Min Range: -4.2508

Max Act: 3.8103. Min Act: -0.1700

Data Index: 1439716 (Python Code)

Max Activating Token Index: 335

Text #17

Max Range: 4.2508. Min Range: -4.2508

Max Act: 3.8038. Min Act: -0.1700

Data Index: 843954 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 4.2508. Min Range: -4.2508

Max Act: 3.7822. Min Act: -0.1700

Data Index: 1501283 (Python Code)

Max Activating Token Index: 622

Text #19

Max Range: 4.2508. Min Range: -4.2508

Max Act: 3.7976. Min Act: -0.1700

Data Index: 1361413 (Python Code)

Max Activating Token Index: 230