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

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

Neuron 1304 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: 3.9525. Min Range: -3.9525

Max Act: 3.9525. Min Act: -0.1700

Data Index: 1450759 (Python Code)

Max Activating Token Index: 536

Text #1

Max Range: 3.9525. Min Range: -3.9525

Max Act: 3.8963. Min Act: -0.1700

Data Index: 1447676 (Python Code)

Max Activating Token Index: 145

Text #2

Max Range: 3.9525. Min Range: -3.9525

Max Act: 3.8712. Min Act: -0.1700

Data Index: 1580095 (Python Code)

Max Activating Token Index: 684

Text #3

Max Range: 3.9525. Min Range: -3.9525

Max Act: 3.8670. Min Act: -0.1700

Data Index: 1445526 (Python Code)

Max Activating Token Index: 890

Text #4

Max Range: 3.9525. Min Range: -3.9525

Max Act: 3.8392. Min Act: -0.1700

Data Index: 1417530 (Python Code)

Max Activating Token Index: 411

Text #5

Max Range: 3.9525. Min Range: -3.9525

Max Act: 3.7855. Min Act: -0.1700

Data Index: 1469174 (Python Code)

Max Activating Token Index: 754

Text #6

Max Range: 3.9525. Min Range: -3.9525

Max Act: 3.8070. Min Act: -0.1700

Data Index: 1505437 (Python Code)

Max Activating Token Index: 874

Text #7

Max Range: 3.9525. Min Range: -3.9525

Max Act: 3.7980. Min Act: -0.1700

Data Index: 1429911 (Python Code)

Max Activating Token Index: 153

Text #8

Max Range: 3.9525. Min Range: -3.9525

Max Act: 3.7571. Min Act: -0.1700

Data Index: 1559835 (Python Code)

Max Activating Token Index: 1006

Text #9

Max Range: 3.9525. Min Range: -3.9525

Max Act: 3.7784. Min Act: -0.1700

Data Index: 1654948 (Python Code)

Max Activating Token Index: 446

Text #10

Max Range: 3.9525. Min Range: -3.9525

Max Act: 3.7579. Min Act: -0.1700

Data Index: 1418030 (Python Code)

Max Activating Token Index: 264

Text #11

Max Range: 3.9525. Min Range: -3.9525

Max Act: 3.7766. Min Act: -0.1700

Data Index: 1608140 (Python Code)

Max Activating Token Index: 855

Text #12

Max Range: 3.9525. Min Range: -3.9525

Max Act: 3.7612. Min Act: -0.1700

Data Index: 1431727 (Python Code)

Max Activating Token Index: 851

Text #13

Max Range: 3.9525. Min Range: -3.9525

Max Act: 3.7558. Min Act: -0.1700

Data Index: 655070 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 3.9525. Min Range: -3.9525

Max Act: 3.7378. Min Act: -0.1700

Data Index: 1596596 (Python Code)

Max Activating Token Index: 790

Text #15

Max Range: 3.9525. Min Range: -3.9525

Max Act: 3.7723. Min Act: -0.1700

Data Index: 1645453 (Python Code)

Max Activating Token Index: 845

Text #16

Max Range: 3.9525. Min Range: -3.9525

Max Act: 3.7564. Min Act: -0.1700

Data Index: 1561814 (Python Code)

Max Activating Token Index: 548

Text #17

Max Range: 3.9525. Min Range: -3.9525

Max Act: 3.7616. Min Act: -0.1700

Data Index: 1602204 (Python Code)

Max Activating Token Index: 1016

Text #18

Max Range: 3.9525. Min Range: -3.9525

Max Act: 3.7632. Min Act: -0.1700

Data Index: 1467082 (Python Code)

Max Activating Token Index: 85

Text #19

Max Range: 3.9525. Min Range: -3.9525

Max Act: 3.7456. Min Act: -0.1700

Data Index: 653287 (C4 (Web Text))

Max Activating Token Index: 562