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

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

Neuron 177 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.9357. Min Act: -0.1700

Data Index: 995265 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.8732. Min Act: -0.1700

Data Index: 110953 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.8107. Min Act: -0.1700

Data Index: 117666 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.7482. Min Act: -0.1700

Data Index: 250853 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.7170. Min Act: -0.1700

Data Index: 624471 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.7170. Min Act: -0.1700

Data Index: 1000928 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.6857. Min Act: -0.1700

Data Index: 1313803 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.6857. Min Act: -0.1700

Data Index: 800266 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.6545. Min Act: -0.1700

Data Index: 1177819 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.5920. Min Act: -0.1700

Data Index: 203168 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.6232. Min Act: -0.1700

Data Index: 452902 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.6232. Min Act: -0.1700

Data Index: 587227 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.5607. Min Act: -0.1700

Data Index: 124940 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.5920. Min Act: -0.1700

Data Index: 591680 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.5920. Min Act: -0.1700

Data Index: 382642 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.5607. Min Act: -0.1700

Data Index: 1037254 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.4982. Min Act: -0.1700

Data Index: 1149420 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.5295. Min Act: -0.1700

Data Index: 1084768 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.5920. Min Act: -0.1700

Data Index: 806349 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 5.9357. Min Range: -5.9357

Max Act: 5.5295. Min Act: -0.1700

Data Index: 918988 (C4 (Web Text))

Max Activating Token Index: 440