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

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

Neuron 692 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: 7.5619. Min Range: -7.5619

Max Act: 7.5619. Min Act: -0.1700

Data Index: 1140797 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 7.5619. Min Range: -7.5619

Max Act: 7.5307. Min Act: -0.1700

Data Index: 1231896 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 7.5619. Min Range: -7.5619

Max Act: 7.4994. Min Act: -0.1700

Data Index: 924165 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 7.5619. Min Range: -7.5619

Max Act: 7.4369. Min Act: -0.1700

Data Index: 1173503 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 7.5619. Min Range: -7.5619

Max Act: 7.4994. Min Act: -0.1700

Data Index: 526631 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 7.5619. Min Range: -7.5619

Max Act: 7.3119. Min Act: -0.1700

Data Index: 268859 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 7.5619. Min Range: -7.5619

Max Act: 7.2494. Min Act: -0.1700

Data Index: 43816 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 7.5619. Min Range: -7.5619

Max Act: 7.3119. Min Act: -0.1700

Data Index: 273986 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 7.5619. Min Range: -7.5619

Max Act: 7.2494. Min Act: -0.1700

Data Index: 931081 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 7.5619. Min Range: -7.5619

Max Act: 7.3119. Min Act: -0.1700

Data Index: 1022807 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 7.5619. Min Range: -7.5619

Max Act: 7.3432. Min Act: -0.1700

Data Index: 1004198 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 7.5619. Min Range: -7.5619

Max Act: 7.3432. Min Act: -0.1700

Data Index: 1286754 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 7.5619. Min Range: -7.5619

Max Act: 7.2494. Min Act: -0.1700

Data Index: 277793 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 7.5619. Min Range: -7.5619

Max Act: 7.1869. Min Act: -0.1700

Data Index: 916474 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 7.5619. Min Range: -7.5619

Max Act: 7.2494. Min Act: -0.1700

Data Index: 611938 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 7.5619. Min Range: -7.5619

Max Act: 7.2494. Min Act: -0.1700

Data Index: 922198 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 7.5619. Min Range: -7.5619

Max Act: 7.2494. Min Act: -0.1700

Data Index: 1223754 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 7.5619. Min Range: -7.5619

Max Act: 7.2182. Min Act: -0.1700

Data Index: 895521 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 7.5619. Min Range: -7.5619

Max Act: 7.3119. Min Act: -0.1700

Data Index: 313680 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 7.5619. Min Range: -7.5619

Max Act: 7.2807. Min Act: -0.1700

Data Index: 89464 (C4 (Web Text))

Max Activating Token Index: 133