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

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

Neuron 1663 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5025. Min Range: -5.5025

Max Act: 5.5025. Min Act: -0.1700

Data Index: 116091 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 5.5025. Min Range: -5.5025

Max Act: 5.3775. Min Act: -0.1700

Data Index: 956650 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 5.5025. Min Range: -5.5025

Max Act: 5.3463. Min Act: -0.1700

Data Index: 100669 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 5.5025. Min Range: -5.5025

Max Act: 5.3463. Min Act: -0.1700

Data Index: 464671 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 5.5025. Min Range: -5.5025

Max Act: 5.3775. Min Act: -0.1700

Data Index: 1181770 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 5.5025. Min Range: -5.5025

Max Act: 5.3150. Min Act: -0.1700

Data Index: 112954 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 5.5025. Min Range: -5.5025

Max Act: 5.2525. Min Act: -0.1700

Data Index: 798732 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 5.5025. Min Range: -5.5025

Max Act: 5.1900. Min Act: -0.1700

Data Index: 960295 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 5.5025. Min Range: -5.5025

Max Act: 5.1900. Min Act: -0.1700

Data Index: 900476 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 5.5025. Min Range: -5.5025

Max Act: 5.1588. Min Act: -0.1700

Data Index: 407939 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 5.5025. Min Range: -5.5025

Max Act: 5.2213. Min Act: -0.1700

Data Index: 52741 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 5.5025. Min Range: -5.5025

Max Act: 5.1275. Min Act: -0.1700

Data Index: 516172 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 5.5025. Min Range: -5.5025

Max Act: 5.1275. Min Act: -0.1700

Data Index: 497614 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 5.5025. Min Range: -5.5025

Max Act: 5.1588. Min Act: -0.1700

Data Index: 2690 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 5.5025. Min Range: -5.5025

Max Act: 5.1900. Min Act: -0.1700

Data Index: 180204 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 5.5025. Min Range: -5.5025

Max Act: 5.1588. Min Act: -0.1700

Data Index: 1212900 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 5.5025. Min Range: -5.5025

Max Act: 5.1900. Min Act: -0.1700

Data Index: 97970 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 5.5025. Min Range: -5.5025

Max Act: 5.1588. Min Act: -0.1700

Data Index: 198190 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 5.5025. Min Range: -5.5025

Max Act: 5.1900. Min Act: -0.1700

Data Index: 781548 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 5.5025. Min Range: -5.5025

Max Act: 5.1900. Min Act: -0.1700

Data Index: 176520 (C4 (Web Text))

Max Activating Token Index: 754