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

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

Neuron 1622 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7780. Min Range: -5.7780

Max Act: 5.7780. Min Act: -0.1700

Data Index: 930376 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 5.7780. Min Range: -5.7780

Max Act: 5.7780. Min Act: -0.1700

Data Index: 698943 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 5.7780. Min Range: -5.7780

Max Act: 5.7155. Min Act: -0.1700

Data Index: 1357785 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 5.7780. Min Range: -5.7780

Max Act: 5.6530. Min Act: -0.1700

Data Index: 167998 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 5.7780. Min Range: -5.7780

Max Act: 5.6530. Min Act: -0.1700

Data Index: 1152513 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 5.7780. Min Range: -5.7780

Max Act: 5.6530. Min Act: -0.1700

Data Index: 776576 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 5.7780. Min Range: -5.7780

Max Act: 5.6530. Min Act: -0.1700

Data Index: 133907 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 5.7780. Min Range: -5.7780

Max Act: 5.6218. Min Act: -0.1700

Data Index: 723984 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 5.7780. Min Range: -5.7780

Max Act: 5.5905. Min Act: -0.1700

Data Index: 974648 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 5.7780. Min Range: -5.7780

Max Act: 5.5593. Min Act: -0.1700

Data Index: 1298536 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 5.7780. Min Range: -5.7780

Max Act: 5.5905. Min Act: -0.1700

Data Index: 783717 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 5.7780. Min Range: -5.7780

Max Act: 5.5280. Min Act: -0.1700

Data Index: 513794 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 5.7780. Min Range: -5.7780

Max Act: 5.5905. Min Act: -0.1700

Data Index: 1310320 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 5.7780. Min Range: -5.7780

Max Act: 5.5280. Min Act: -0.1700

Data Index: 228085 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 5.7780. Min Range: -5.7780

Max Act: 5.5280. Min Act: -0.1700

Data Index: 118344 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 5.7780. Min Range: -5.7780

Max Act: 5.5280. Min Act: -0.1700

Data Index: 185607 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 5.7780. Min Range: -5.7780

Max Act: 5.5280. Min Act: -0.1700

Data Index: 1155082 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 5.7780. Min Range: -5.7780

Max Act: 5.5280. Min Act: -0.1700

Data Index: 649924 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 5.7780. Min Range: -5.7780

Max Act: 5.4968. Min Act: -0.1700

Data Index: 707042 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 5.7780. Min Range: -5.7780

Max Act: 5.4968. Min Act: -0.1700

Data Index: 1002259 (C4 (Web Text))

Max Activating Token Index: 652