Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 247 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.3865. Min Range: -5.3865

Max Act: 5.3865. Min Act: -0.1700

Data Index: 334892 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 5.3865. Min Range: -5.3865

Max Act: 5.1052. Min Act: -0.1700

Data Index: 714942 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 5.3865. Min Range: -5.3865

Max Act: 5.0740. Min Act: -0.1700

Data Index: 834867 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 5.3865. Min Range: -5.3865

Max Act: 5.0740. Min Act: -0.1700

Data Index: 1097850 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 5.3865. Min Range: -5.3865

Max Act: 5.0427. Min Act: -0.1700

Data Index: 50078 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 5.3865. Min Range: -5.3865

Max Act: 5.0427. Min Act: -0.1700

Data Index: 301356 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 5.3865. Min Range: -5.3865

Max Act: 4.9802. Min Act: -0.1700

Data Index: 798564 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 5.3865. Min Range: -5.3865

Max Act: 4.9802. Min Act: -0.1700

Data Index: 631745 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 5.3865. Min Range: -5.3865

Max Act: 5.0115. Min Act: -0.1700

Data Index: 57068 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 5.3865. Min Range: -5.3865

Max Act: 4.9802. Min Act: -0.1700

Data Index: 1030895 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 5.3865. Min Range: -5.3865

Max Act: 4.9802. Min Act: -0.1700

Data Index: 856005 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 5.3865. Min Range: -5.3865

Max Act: 4.9177. Min Act: -0.1700

Data Index: 521448 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 5.3865. Min Range: -5.3865

Max Act: 4.9177. Min Act: -0.1700

Data Index: 996326 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 5.3865. Min Range: -5.3865

Max Act: 4.9177. Min Act: -0.1700

Data Index: 812054 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 5.3865. Min Range: -5.3865

Max Act: 4.9177. Min Act: -0.1700

Data Index: 602240 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 5.3865. Min Range: -5.3865

Max Act: 4.8552. Min Act: -0.1700

Data Index: 451637 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 5.3865. Min Range: -5.3865

Max Act: 4.9177. Min Act: -0.1700

Data Index: 435679 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 5.3865. Min Range: -5.3865

Max Act: 4.8552. Min Act: -0.1700

Data Index: 620341 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 5.3865. Min Range: -5.3865

Max Act: 4.8240. Min Act: -0.1700

Data Index: 498022 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 5.3865. Min Range: -5.3865

Max Act: 4.8240. Min Act: -0.1700

Data Index: 291910 (C4 (Web Text))

Max Activating Token Index: 404