Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1838 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.6236. Min Act: -0.1700

Data Index: 1312526 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.5923. Min Act: -0.1700

Data Index: 600649 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.5296. Min Act: -0.1700

Data Index: 1098939 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.6236. Min Act: -0.1700

Data Index: 1002200 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.5923. Min Act: -0.1700

Data Index: 459906 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.5296. Min Act: -0.1700

Data Index: 397120 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.5610. Min Act: -0.1700

Data Index: 743432 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.5296. Min Act: -0.1700

Data Index: 100855 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.5296. Min Act: -0.1700

Data Index: 468154 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.5610. Min Act: -0.1700

Data Index: 805623 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.5296. Min Act: -0.1700

Data Index: 978577 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.4983. Min Act: -0.1700

Data Index: 655839 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.5923. Min Act: -0.1700

Data Index: 870657 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.5296. Min Act: -0.1700

Data Index: 565330 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.5296. Min Act: -0.1700

Data Index: 778332 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.5923. Min Act: -0.1700

Data Index: 1272093 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.4983. Min Act: -0.1700

Data Index: 196723 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.4669. Min Act: -0.1700

Data Index: 425267 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.5296. Min Act: -0.1700

Data Index: 203928 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.4983. Min Act: -0.1700

Data Index: 622104 (C4 (Web Text))

Max Activating Token Index: 51