Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1654 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.8194. Min Act: -0.1700

Data Index: 1434695 (Python Code)

Max Activating Token Index: 838

Text #1

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.8194. Min Act: -0.1700

Data Index: 1428830 (Python Code)

Max Activating Token Index: 780

Text #2

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.6943. Min Act: -0.1700

Data Index: 1582263 (Python Code)

Max Activating Token Index: 771

Text #3

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.6943. Min Act: -0.1700

Data Index: 1469555 (Python Code)

Max Activating Token Index: 747

Text #4

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.6943. Min Act: -0.1700

Data Index: 1511605 (Python Code)

Max Activating Token Index: 561

Text #5

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.6317. Min Act: -0.1700

Data Index: 1479091 (Python Code)

Max Activating Token Index: 141

Text #6

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.6003. Min Act: -0.1700

Data Index: 1455148 (Python Code)

Max Activating Token Index: 927

Text #7

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.6003. Min Act: -0.1700

Data Index: 1542537 (Python Code)

Max Activating Token Index: 634

Text #8

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.5534. Min Act: -0.1700

Data Index: 1584069 (Python Code)

Max Activating Token Index: 832

Text #9

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4907. Min Act: -0.1700

Data Index: 1609737 (Python Code)

Max Activating Token Index: 724

Text #10

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.5064. Min Act: -0.1700

Data Index: 1365465 (Python Code)

Max Activating Token Index: 866

Text #11

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.5377. Min Act: -0.1700

Data Index: 1596701 (Python Code)

Max Activating Token Index: 961

Text #12

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.5220. Min Act: -0.1700

Data Index: 1560051 (Python Code)

Max Activating Token Index: 807

Text #13

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.5220. Min Act: -0.1700

Data Index: 1494554 (Python Code)

Max Activating Token Index: 559

Text #14

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.5064. Min Act: -0.1700

Data Index: 1510031 (Python Code)

Max Activating Token Index: 103

Text #15

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4750. Min Act: -0.1700

Data Index: 1584734 (Python Code)

Max Activating Token Index: 203

Text #16

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4907. Min Act: -0.1700

Data Index: 1161977 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4594. Min Act: -0.1700

Data Index: 78298 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4594. Min Act: -0.1700

Data Index: 1386542 (Python Code)

Max Activating Token Index: 106

Text #19

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.4437. Min Act: -0.1700

Data Index: 1490706 (Python Code)

Max Activating Token Index: 459