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

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

Neuron 1579 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: 3.3538. Min Range: -3.3538

Max Act: 3.3538. Min Act: -0.1700

Data Index: 1554303 (Python Code)

Max Activating Token Index: 618

Text #1

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.3472. Min Act: -0.1700

Data Index: 1478626 (Python Code)

Max Activating Token Index: 450

Text #2

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.3263. Min Act: -0.1700

Data Index: 1382559 (Python Code)

Max Activating Token Index: 815

Text #3

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.2910. Min Act: -0.1700

Data Index: 1544903 (Python Code)

Max Activating Token Index: 840

Text #4

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.3165. Min Act: -0.1700

Data Index: 1624836 (Python Code)

Max Activating Token Index: 248

Text #5

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.2748. Min Act: -0.1700

Data Index: 1432803 (Python Code)

Max Activating Token Index: 395

Text #6

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.2599. Min Act: -0.1700

Data Index: 447863 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.2810. Min Act: -0.1700

Data Index: 1371306 (Python Code)

Max Activating Token Index: 798

Text #8

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.2638. Min Act: -0.1700

Data Index: 1549778 (Python Code)

Max Activating Token Index: 656

Text #9

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.2556. Min Act: -0.1699

Data Index: 1417260 (Python Code)

Max Activating Token Index: 111

Text #10

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.2304. Min Act: -0.1700

Data Index: 1468086 (Python Code)

Max Activating Token Index: 992

Text #11

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.2320. Min Act: -0.1700

Data Index: 1493765 (Python Code)

Max Activating Token Index: 768

Text #12

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.2053. Min Act: -0.1700

Data Index: 1385860 (Python Code)

Max Activating Token Index: 837

Text #13

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.2176. Min Act: -0.1700

Data Index: 1415287 (Python Code)

Max Activating Token Index: 247

Text #14

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.2028. Min Act: -0.1700

Data Index: 1365113 (Python Code)

Max Activating Token Index: 975

Text #15

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.1857. Min Act: -0.1700

Data Index: 1407466 (Python Code)

Max Activating Token Index: 879

Text #16

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.1861. Min Act: -0.1700

Data Index: 1539599 (Python Code)

Max Activating Token Index: 518

Text #17

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.2241. Min Act: -0.1700

Data Index: 1432910 (Python Code)

Max Activating Token Index: 986

Text #18

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.1842. Min Act: -0.1700

Data Index: 1380075 (Python Code)

Max Activating Token Index: 991

Text #19

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.1740. Min Act: -0.1700

Data Index: 1514663 (Python Code)

Max Activating Token Index: 49