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

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

Neuron 1392 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: 4.2308. Min Range: -4.2308

Max Act: 4.2308. Min Act: -0.1700

Data Index: 1616188 (Python Code)

Max Activating Token Index: 349

Text #1

Max Range: 4.2308. Min Range: -4.2308

Max Act: 4.0917. Min Act: -0.1700

Data Index: 1474207 (Python Code)

Max Activating Token Index: 368

Text #2

Max Range: 4.2308. Min Range: -4.2308

Max Act: 4.0503. Min Act: -0.1700

Data Index: 1630587 (Python Code)

Max Activating Token Index: 506

Text #3

Max Range: 4.2308. Min Range: -4.2308

Max Act: 4.0477. Min Act: -0.1700

Data Index: 1602341 (Python Code)

Max Activating Token Index: 384

Text #4

Max Range: 4.2308. Min Range: -4.2308

Max Act: 4.0593. Min Act: -0.1700

Data Index: 1371267 (Python Code)

Max Activating Token Index: 580

Text #5

Max Range: 4.2308. Min Range: -4.2308

Max Act: 4.0301. Min Act: -0.1700

Data Index: 761291 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 4.2308. Min Range: -4.2308

Max Act: 4.0046. Min Act: -0.1700

Data Index: 703555 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 4.2308. Min Range: -4.2308

Max Act: 3.9763. Min Act: -0.1700

Data Index: 1469876 (Python Code)

Max Activating Token Index: 299

Text #8

Max Range: 4.2308. Min Range: -4.2308

Max Act: 3.9718. Min Act: -0.1700

Data Index: 1620127 (Python Code)

Max Activating Token Index: 34

Text #9

Max Range: 4.2308. Min Range: -4.2308

Max Act: 3.9905. Min Act: -0.1700

Data Index: 1487446 (Python Code)

Max Activating Token Index: 368

Text #10

Max Range: 4.2308. Min Range: -4.2308

Max Act: 3.9856. Min Act: -0.1700

Data Index: 1613495 (Python Code)

Max Activating Token Index: 531

Text #11

Max Range: 4.2308. Min Range: -4.2308

Max Act: 3.9404. Min Act: -0.1700

Data Index: 407471 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 4.2308. Min Range: -4.2308

Max Act: 3.9349. Min Act: -0.1700

Data Index: 381565 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 4.2308. Min Range: -4.2308

Max Act: 3.9128. Min Act: -0.1700

Data Index: 497206 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 4.2308. Min Range: -4.2308

Max Act: 3.9399. Min Act: -0.1700

Data Index: 673350 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 4.2308. Min Range: -4.2308

Max Act: 3.8899. Min Act: -0.1700

Data Index: 253815 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 4.2308. Min Range: -4.2308

Max Act: 3.8780. Min Act: -0.1700

Data Index: 1565059 (Python Code)

Max Activating Token Index: 294

Text #17

Max Range: 4.2308. Min Range: -4.2308

Max Act: 3.8997. Min Act: -0.1700

Data Index: 1512110 (Python Code)

Max Activating Token Index: 665

Text #18

Max Range: 4.2308. Min Range: -4.2308

Max Act: 3.8961. Min Act: -0.1700

Data Index: 1643816 (Python Code)

Max Activating Token Index: 827

Text #19

Max Range: 4.2308. Min Range: -4.2308

Max Act: 3.8457. Min Act: -0.1700

Data Index: 1499927 (Python Code)

Max Activating Token Index: 87