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

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

Neuron 729 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.6384. Min Act: -0.1700

Data Index: 1217608 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.5758. Min Act: -0.1700

Data Index: 94366 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.5915. Min Act: -0.1700

Data Index: 687856 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.4975. Min Act: -0.1700

Data Index: 1183200 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.3720. Min Act: -0.1700

Data Index: 1116892 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.3720. Min Act: -0.1700

Data Index: 1049406 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.3407. Min Act: -0.1700

Data Index: 1295665 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.3250. Min Act: -0.1700

Data Index: 132327 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.3093. Min Act: -0.1700

Data Index: 672626 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.2778. Min Act: -0.1700

Data Index: 348588 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.2935. Min Act: -0.1700

Data Index: 1288521 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.2778. Min Act: -0.1700

Data Index: 575418 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.2778. Min Act: -0.1700

Data Index: 312307 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.2778. Min Act: -0.1700

Data Index: 733203 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.2778. Min Act: -0.1700

Data Index: 1156261 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.2621. Min Act: -0.1700

Data Index: 1342955 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.2307. Min Act: -0.1700

Data Index: 746198 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.2307. Min Act: -0.1700

Data Index: 379932 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.2621. Min Act: -0.1700

Data Index: 551507 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 3.6384. Min Range: -3.6384

Max Act: 3.2621. Min Act: -0.1700

Data Index: 638959 (C4 (Web Text))

Max Activating Token Index: 15