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

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

Neuron 1897 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.6487. Min Act: -0.1700

Data Index: 845142 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.6487. Min Act: -0.1700

Data Index: 1315124 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.6487. Min Act: -0.1700

Data Index: 560574 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.6487. Min Act: -0.1700

Data Index: 675929 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.6174. Min Act: -0.1700

Data Index: 732131 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.5861. Min Act: -0.1700

Data Index: 1252736 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.5861. Min Act: -0.1700

Data Index: 868011 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.5548. Min Act: -0.1700

Data Index: 296084 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.5548. Min Act: -0.1700

Data Index: 962761 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.5548. Min Act: -0.1700

Data Index: 1221290 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.5234. Min Act: -0.1700

Data Index: 729377 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.5548. Min Act: -0.1700

Data Index: 591265 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.5548. Min Act: -0.1700

Data Index: 45078 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.5548. Min Act: -0.1700

Data Index: 1293647 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.5234. Min Act: -0.1700

Data Index: 665273 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.4607. Min Act: -0.1700

Data Index: 1030487 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.5234. Min Act: -0.1700

Data Index: 413907 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.5234. Min Act: -0.1700

Data Index: 268442 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.5234. Min Act: -0.1700

Data Index: 492828 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.5234. Min Act: -0.1700

Data Index: 719475 (C4 (Web Text))

Max Activating Token Index: 884