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

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

Neuron 681 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: 2.9496. Min Range: -2.9496

Max Act: 2.9496. Min Act: -0.1700

Data Index: 1582306 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 2.9496. Min Range: -2.9496

Max Act: 2.8598. Min Act: -0.1022

Data Index: 1444045 (Python Code)

Max Activating Token Index: 931

Text #2

Max Range: 2.9496. Min Range: -2.9496

Max Act: 2.8613. Min Act: -0.1699

Data Index: 1532983 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 2.9496. Min Range: -2.9496

Max Act: 2.8682. Min Act: -0.1700

Data Index: 1406738 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 2.9496. Min Range: -2.9496

Max Act: 2.8250. Min Act: -0.1700

Data Index: 1374163 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 2.9496. Min Range: -2.9496

Max Act: 2.7908. Min Act: -0.1697

Data Index: 1378855 (Python Code)

Max Activating Token Index: 415

Text #6

Max Range: 2.9496. Min Range: -2.9496

Max Act: 2.7909. Min Act: -0.1700

Data Index: 1549719 (Python Code)

Max Activating Token Index: 771

Text #7

Max Range: 2.9496. Min Range: -2.9496

Max Act: 2.7708. Min Act: -0.1698

Data Index: 1591029 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 2.9496. Min Range: -2.9496

Max Act: 2.7956. Min Act: -0.1022

Data Index: 1500924 (Python Code)

Max Activating Token Index: 532

Text #9

Max Range: 2.9496. Min Range: -2.9496

Max Act: 2.7804. Min Act: -0.1700

Data Index: 1519654 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 2.9496. Min Range: -2.9496

Max Act: 2.7893. Min Act: -0.1551

Data Index: 1452660 (Python Code)

Max Activating Token Index: 680

Text #11

Max Range: 2.9496. Min Range: -2.9496

Max Act: 2.7774. Min Act: -0.1700

Data Index: 580579 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 2.9496. Min Range: -2.9496

Max Act: 2.7558. Min Act: -0.1700

Data Index: 1255990 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 2.9496. Min Range: -2.9496

Max Act: 2.7590. Min Act: -0.1022

Data Index: 1412426 (Python Code)

Max Activating Token Index: 175

Text #14

Max Range: 2.9496. Min Range: -2.9496

Max Act: 2.7410. Min Act: -0.1700

Data Index: 1628005 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 2.9496. Min Range: -2.9496

Max Act: 2.7379. Min Act: -0.1700

Data Index: 1399485 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 2.9496. Min Range: -2.9496

Max Act: 2.7552. Min Act: -0.1649

Data Index: 1580960 (Python Code)

Max Activating Token Index: 382

Text #17

Max Range: 2.9496. Min Range: -2.9496

Max Act: 2.7484. Min Act: -0.1700

Data Index: 1577256 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 2.9496. Min Range: -2.9496

Max Act: 2.7631. Min Act: -0.1022

Data Index: 1576909 (Python Code)

Max Activating Token Index: 819

Text #19

Max Range: 2.9496. Min Range: -2.9496

Max Act: 2.7579. Min Act: -0.1636

Data Index: 583397 (C4 (Web Text))

Max Activating Token Index: 227