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

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

Neuron 568 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: 7.3735. Min Range: -7.3735

Max Act: 7.3423. Min Act: -0.1700

Data Index: 1258480 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 7.3735. Min Range: -7.3735

Max Act: 7.2485. Min Act: -0.1700

Data Index: 681294 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 7.3735. Min Range: -7.3735

Max Act: 7.3735. Min Act: -0.1700

Data Index: 1397064 (Python Code)

Max Activating Token Index: 919

Text #3

Max Range: 7.3735. Min Range: -7.3735

Max Act: 7.0610. Min Act: -0.1700

Data Index: 1584814 (Python Code)

Max Activating Token Index: 690

Text #4

Max Range: 7.3735. Min Range: -7.3735

Max Act: 7.2173. Min Act: -0.1700

Data Index: 1598228 (Python Code)

Max Activating Token Index: 747

Text #5

Max Range: 7.3735. Min Range: -7.3735

Max Act: 7.0298. Min Act: -0.1700

Data Index: 1386484 (Python Code)

Max Activating Token Index: 994

Text #6

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.9360. Min Act: -0.1700

Data Index: 200905 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.9360. Min Act: -0.1700

Data Index: 1001387 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.9360. Min Act: -0.1700

Data Index: 37325 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.8735. Min Act: -0.1700

Data Index: 940706 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.8735. Min Act: -0.1700

Data Index: 1136719 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.7485. Min Act: -0.1700

Data Index: 1582877 (Python Code)

Max Activating Token Index: 809

Text #12

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.7485. Min Act: -0.1700

Data Index: 1543340 (Python Code)

Max Activating Token Index: 918

Text #13

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.8423. Min Act: -0.1700

Data Index: 554179 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.8110. Min Act: -0.1700

Data Index: 911254 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.8110. Min Act: -0.1700

Data Index: 283950 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.8110. Min Act: -0.1700

Data Index: 1400293 (Python Code)

Max Activating Token Index: 150

Text #17

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.8110. Min Act: -0.1700

Data Index: 586718 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.7798. Min Act: -0.1700

Data Index: 1406514 (Python Code)

Max Activating Token Index: 265

Text #19

Max Range: 7.3735. Min Range: -7.3735

Max Act: 6.7485. Min Act: -0.1700

Data Index: 1459051 (Python Code)

Max Activating Token Index: 509