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

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

Neuron 2025 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: 5.4432. Min Range: -5.4432

Max Act: 5.4432. Min Act: -0.1700

Data Index: 927942 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 5.4432. Min Range: -5.4432

Max Act: 5.2245. Min Act: -0.1700

Data Index: 722316 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 5.4432. Min Range: -5.4432

Max Act: 5.1620. Min Act: -0.1700

Data Index: 1277697 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 5.4432. Min Range: -5.4432

Max Act: 5.0370. Min Act: -0.1700

Data Index: 599360 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 5.4432. Min Range: -5.4432

Max Act: 5.1620. Min Act: -0.1700

Data Index: 485125 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 5.4432. Min Range: -5.4432

Max Act: 5.2557. Min Act: -0.1700

Data Index: 146139 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 5.4432. Min Range: -5.4432

Max Act: 5.1307. Min Act: -0.1700

Data Index: 181520 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 5.4432. Min Range: -5.4432

Max Act: 5.1620. Min Act: -0.1700

Data Index: 425259 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 5.4432. Min Range: -5.4432

Max Act: 5.1307. Min Act: -0.1700

Data Index: 47948 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 5.4432. Min Range: -5.4432

Max Act: 5.1307. Min Act: -0.1700

Data Index: 896359 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 5.4432. Min Range: -5.4432

Max Act: 4.9745. Min Act: -0.1700

Data Index: 944316 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 5.4432. Min Range: -5.4432

Max Act: 5.0682. Min Act: -0.1700

Data Index: 231748 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 5.4432. Min Range: -5.4432

Max Act: 5.1932. Min Act: -0.1700

Data Index: 1028736 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 5.4432. Min Range: -5.4432

Max Act: 5.0682. Min Act: -0.1699

Data Index: 229878 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 5.4432. Min Range: -5.4432

Max Act: 4.9432. Min Act: -0.1700

Data Index: 625048 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 5.4432. Min Range: -5.4432

Max Act: 4.8807. Min Act: -0.1700

Data Index: 905524 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 5.4432. Min Range: -5.4432

Max Act: 5.0682. Min Act: -0.1700

Data Index: 1031462 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 5.4432. Min Range: -5.4432

Max Act: 5.0370. Min Act: -0.1700

Data Index: 902597 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 5.4432. Min Range: -5.4432

Max Act: 5.1307. Min Act: -0.1700

Data Index: 555918 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 5.4432. Min Range: -5.4432

Max Act: 4.9745. Min Act: -0.1700

Data Index: 1057646 (C4 (Web Text))

Max Activating Token Index: 38