Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1778 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.5031. Min Act: -0.1700

Data Index: 9071 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.2520. Min Act: -0.1700

Data Index: 583077 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.1419. Min Act: -0.1700

Data Index: 902148 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.1419. Min Act: -0.1700

Data Index: 820439 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.1261. Min Act: -0.1700

Data Index: 939710 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.1104. Min Act: -0.1700

Data Index: 610171 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.0946. Min Act: -0.1700

Data Index: 1184832 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.1104. Min Act: -0.1700

Data Index: 1162234 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.0946. Min Act: -0.1700

Data Index: 92759 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.0946. Min Act: -0.1700

Data Index: 515775 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.0788. Min Act: -0.1700

Data Index: 774364 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.0631. Min Act: -0.1700

Data Index: 161134 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.0788. Min Act: -0.1700

Data Index: 254864 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.0788. Min Act: -0.1700

Data Index: 323008 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.0788. Min Act: -0.1700

Data Index: 1143787 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.0631. Min Act: -0.1700

Data Index: 517887 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.0473. Min Act: -0.1700

Data Index: 527419 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.0631. Min Act: -0.1700

Data Index: 700974 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.0631. Min Act: -0.1700

Data Index: 1114891 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 3.5031. Min Range: -3.5031

Max Act: 3.0788. Min Act: -0.1700

Data Index: 654412 (C4 (Web Text))

Max Activating Token Index: 44