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

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

Neuron 336 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: 3.7042. Min Range: -3.7042

Max Act: 3.7042. Min Act: -0.1700

Data Index: 1490855 (Python Code)

Max Activating Token Index: 691

Text #1

Max Range: 3.7042. Min Range: -3.7042

Max Act: 3.6318. Min Act: -0.1700

Data Index: 1455354 (Python Code)

Max Activating Token Index: 254

Text #2

Max Range: 3.7042. Min Range: -3.7042

Max Act: 3.5315. Min Act: -0.1700

Data Index: 210112 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 3.7042. Min Range: -3.7042

Max Act: 3.5413. Min Act: -0.1700

Data Index: 1544621 (Python Code)

Max Activating Token Index: 945

Text #4

Max Range: 3.7042. Min Range: -3.7042

Max Act: 3.5408. Min Act: -0.1700

Data Index: 677756 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 3.7042. Min Range: -3.7042

Max Act: 3.5048. Min Act: -0.1700

Data Index: 1499662 (Python Code)

Max Activating Token Index: 695

Text #6

Max Range: 3.7042. Min Range: -3.7042

Max Act: 3.4934. Min Act: -0.1700

Data Index: 1384481 (Python Code)

Max Activating Token Index: 427

Text #7

Max Range: 3.7042. Min Range: -3.7042

Max Act: 3.4990. Min Act: -0.1700

Data Index: 1473223 (Python Code)

Max Activating Token Index: 544

Text #8

Max Range: 3.7042. Min Range: -3.7042

Max Act: 3.5229. Min Act: -0.1700

Data Index: 1369418 (Python Code)

Max Activating Token Index: 880

Text #9

Max Range: 3.7042. Min Range: -3.7042

Max Act: 3.5174. Min Act: -0.1700

Data Index: 1511738 (Python Code)

Max Activating Token Index: 716

Text #10

Max Range: 3.7042. Min Range: -3.7042

Max Act: 3.5019. Min Act: -0.1700

Data Index: 1543039 (Python Code)

Max Activating Token Index: 537

Text #11

Max Range: 3.7042. Min Range: -3.7042

Max Act: 3.4832. Min Act: -0.1700

Data Index: 1653856 (Python Code)

Max Activating Token Index: 177

Text #12

Max Range: 3.7042. Min Range: -3.7042

Max Act: 3.4670. Min Act: -0.1700

Data Index: 1468754 (Python Code)

Max Activating Token Index: 484

Text #13

Max Range: 3.7042. Min Range: -3.7042

Max Act: 3.4530. Min Act: -0.1700

Data Index: 1425899 (Python Code)

Max Activating Token Index: 982

Text #14

Max Range: 3.7042. Min Range: -3.7042

Max Act: 3.4410. Min Act: -0.1700

Data Index: 1588892 (Python Code)

Max Activating Token Index: 874

Text #15

Max Range: 3.7042. Min Range: -3.7042

Max Act: 3.4703. Min Act: -0.1700

Data Index: 1387369 (Python Code)

Max Activating Token Index: 615

Text #16

Max Range: 3.7042. Min Range: -3.7042

Max Act: 3.4554. Min Act: -0.1700

Data Index: 1501612 (Python Code)

Max Activating Token Index: 788

Text #17

Max Range: 3.7042. Min Range: -3.7042

Max Act: 3.4536. Min Act: -0.1700

Data Index: 1546434 (Python Code)

Max Activating Token Index: 30

Text #18

Max Range: 3.7042. Min Range: -3.7042

Max Act: 3.4193. Min Act: -0.1700

Data Index: 1525200 (Python Code)

Max Activating Token Index: 651

Text #19

Max Range: 3.7042. Min Range: -3.7042

Max Act: 3.4501. Min Act: -0.1700

Data Index: 1507595 (Python Code)

Max Activating Token Index: 55