Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 657 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.8398. Min Act: -0.1700

Data Index: 1075609 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.6677. Min Act: -0.1700

Data Index: 1570146 (Python Code)

Max Activating Token Index: 35

Text #2

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.5658. Min Act: -0.1700

Data Index: 1372470 (Python Code)

Max Activating Token Index: 246

Text #3

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.5229. Min Act: -0.1700

Data Index: 1423316 (Python Code)

Max Activating Token Index: 32

Text #4

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.3225. Min Act: -0.1700

Data Index: 241657 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.2437. Min Act: -0.1700

Data Index: 224075 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.2537. Min Act: -0.1700

Data Index: 157390 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.2080. Min Act: -0.1700

Data Index: 145543 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.2120. Min Act: -0.1700

Data Index: 694225 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.2275. Min Act: -0.1700

Data Index: 165014 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.1704. Min Act: -0.1699

Data Index: 616120 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.1383. Min Act: -0.1700

Data Index: 1323574 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.1040. Min Act: -0.1700

Data Index: 1449776 (Python Code)

Max Activating Token Index: 534

Text #13

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.0797. Min Act: -0.1699

Data Index: 636574 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.0893. Min Act: -0.1700

Data Index: 1232359 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.0503. Min Act: -0.1700

Data Index: 1565817 (Python Code)

Max Activating Token Index: 625

Text #16

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.0263. Min Act: -0.1700

Data Index: 1471127 (Python Code)

Max Activating Token Index: 925

Text #17

Max Range: 7.8398. Min Range: -7.8398

Max Act: 7.0246. Min Act: -0.1700

Data Index: 35208 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 7.8398. Min Range: -7.8398

Max Act: 6.9944. Min Act: -0.1700

Data Index: 1236161 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 7.8398. Min Range: -7.8398

Max Act: 6.9433. Min Act: -0.1700

Data Index: 1648421 (Python Code)

Max Activating Token Index: 114