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

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

Neuron 661 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.7456. Min Act: -0.1700

Data Index: 279241 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.5891. Min Act: -0.1700

Data Index: 1296764 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.3697. Min Act: -0.1700

Data Index: 594153 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.3697. Min Act: -0.1700

Data Index: 317072 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.4324. Min Act: -0.1700

Data Index: 754906 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.4324. Min Act: -0.1700

Data Index: 331880 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.4324. Min Act: -0.1700

Data Index: 147492 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.3383. Min Act: -0.1700

Data Index: 166333 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.3383. Min Act: -0.1700

Data Index: 798141 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.3383. Min Act: -0.1700

Data Index: 386502 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.3069. Min Act: -0.1700

Data Index: 490073 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.4011. Min Act: -0.1700

Data Index: 1136875 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.3697. Min Act: -0.1700

Data Index: 294572 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.4011. Min Act: -0.1700

Data Index: 929019 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.3383. Min Act: -0.1700

Data Index: 827011 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.2755. Min Act: -0.1700

Data Index: 868376 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.3069. Min Act: -0.1700

Data Index: 145877 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.2126. Min Act: -0.1700

Data Index: 1017602 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.3069. Min Act: -0.1700

Data Index: 480570 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 3.7456. Min Range: -3.7456

Max Act: 3.3069. Min Act: -0.1700

Data Index: 499791 (C4 (Web Text))

Max Activating Token Index: 795