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

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

Neuron 1202 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: 5.5731. Min Range: -5.5731

Max Act: 5.4481. Min Act: -0.1700

Data Index: 532040 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 5.5731. Min Range: -5.5731

Max Act: 5.5731. Min Act: -0.1700

Data Index: 774805 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 5.5731. Min Range: -5.5731

Max Act: 5.4481. Min Act: -0.1700

Data Index: 1032830 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 5.5731. Min Range: -5.5731

Max Act: 5.5418. Min Act: -0.1700

Data Index: 873176 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 5.5731. Min Range: -5.5731

Max Act: 5.4168. Min Act: -0.1700

Data Index: 484914 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 5.5731. Min Range: -5.5731

Max Act: 5.4793. Min Act: -0.1700

Data Index: 226006 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 5.5731. Min Range: -5.5731

Max Act: 5.3856. Min Act: -0.1700

Data Index: 940426 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 5.5731. Min Range: -5.5731

Max Act: 5.3856. Min Act: -0.1700

Data Index: 805623 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 5.5731. Min Range: -5.5731

Max Act: 5.3543. Min Act: -0.1700

Data Index: 484713 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 5.5731. Min Range: -5.5731

Max Act: 5.3543. Min Act: -0.1700

Data Index: 664783 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 5.5731. Min Range: -5.5731

Max Act: 5.2606. Min Act: -0.1700

Data Index: 334183 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 5.5731. Min Range: -5.5731

Max Act: 5.2918. Min Act: -0.1700

Data Index: 1301335 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 5.5731. Min Range: -5.5731

Max Act: 5.3543. Min Act: -0.1700

Data Index: 1301225 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 5.5731. Min Range: -5.5731

Max Act: 5.3231. Min Act: -0.1700

Data Index: 230325 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 5.5731. Min Range: -5.5731

Max Act: 5.3543. Min Act: -0.1700

Data Index: 377935 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 5.5731. Min Range: -5.5731

Max Act: 5.2918. Min Act: -0.1700

Data Index: 884455 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 5.5731. Min Range: -5.5731

Max Act: 5.2293. Min Act: -0.1700

Data Index: 17762 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 5.5731. Min Range: -5.5731

Max Act: 5.2606. Min Act: -0.1700

Data Index: 132402 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 5.5731. Min Range: -5.5731

Max Act: 5.2293. Min Act: -0.1700

Data Index: 639692 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 5.5731. Min Range: -5.5731

Max Act: 5.2293. Min Act: -0.1700

Data Index: 583329 (C4 (Web Text))

Max Activating Token Index: 380