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

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

Neuron 829 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: 3.9441. Min Range: -3.9441

Max Act: 3.9441. Min Act: -0.1700

Data Index: 723551 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 3.9441. Min Range: -3.9441

Max Act: 3.8815. Min Act: -0.1700

Data Index: 501462 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 3.9441. Min Range: -3.9441

Max Act: 3.8190. Min Act: -0.1700

Data Index: 556830 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 3.9441. Min Range: -3.9441

Max Act: 3.8190. Min Act: -0.1700

Data Index: 1110045 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 3.9441. Min Range: -3.9441

Max Act: 3.8190. Min Act: -0.1700

Data Index: 227187 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 3.9441. Min Range: -3.9441

Max Act: 3.7877. Min Act: -0.1700

Data Index: 1325831 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 3.9441. Min Range: -3.9441

Max Act: 3.7564. Min Act: -0.1700

Data Index: 647725 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 3.9441. Min Range: -3.9441

Max Act: 3.7877. Min Act: -0.1700

Data Index: 1081400 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 3.9441. Min Range: -3.9441

Max Act: 3.7877. Min Act: -0.1700

Data Index: 497818 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 3.9441. Min Range: -3.9441

Max Act: 3.7564. Min Act: -0.1700

Data Index: 128954 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 3.9441. Min Range: -3.9441

Max Act: 3.7564. Min Act: -0.1700

Data Index: 727108 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 3.9441. Min Range: -3.9441

Max Act: 3.7564. Min Act: -0.1700

Data Index: 152229 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 3.9441. Min Range: -3.9441

Max Act: 3.7251. Min Act: -0.1700

Data Index: 34391 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 3.9441. Min Range: -3.9441

Max Act: 3.6938. Min Act: -0.1700

Data Index: 677320 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 3.9441. Min Range: -3.9441

Max Act: 3.6782. Min Act: -0.1700

Data Index: 1097741 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 3.9441. Min Range: -3.9441

Max Act: 3.7251. Min Act: -0.1700

Data Index: 1321119 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 3.9441. Min Range: -3.9441

Max Act: 3.6938. Min Act: -0.1700

Data Index: 949912 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 3.9441. Min Range: -3.9441

Max Act: 3.6782. Min Act: -0.1700

Data Index: 578738 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 3.9441. Min Range: -3.9441

Max Act: 3.6938. Min Act: -0.1700

Data Index: 552834 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 3.9441. Min Range: -3.9441

Max Act: 3.6782. Min Act: -0.1700

Data Index: 906519 (C4 (Web Text))

Max Activating Token Index: 883