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

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

Neuron 649 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: 4.4144. Min Range: -4.4144

Max Act: 4.4144. Min Act: -0.1700

Data Index: 1393767 (Python Code)

Max Activating Token Index: 244

Text #1

Max Range: 4.4144. Min Range: -4.4144

Max Act: 4.3712. Min Act: -0.1700

Data Index: 1593017 (Python Code)

Max Activating Token Index: 130

Text #2

Max Range: 4.4144. Min Range: -4.4144

Max Act: 4.3524. Min Act: -0.1700

Data Index: 1621865 (Python Code)

Max Activating Token Index: 814

Text #3

Max Range: 4.4144. Min Range: -4.4144

Max Act: 4.3783. Min Act: -0.1700

Data Index: 1494310 (Python Code)

Max Activating Token Index: 553

Text #4

Max Range: 4.4144. Min Range: -4.4144

Max Act: 4.3471. Min Act: -0.1700

Data Index: 1374436 (Python Code)

Max Activating Token Index: 577

Text #5

Max Range: 4.4144. Min Range: -4.4144

Max Act: 4.3356. Min Act: -0.1700

Data Index: 1369791 (Python Code)

Max Activating Token Index: 846

Text #6

Max Range: 4.4144. Min Range: -4.4144

Max Act: 4.3170. Min Act: -0.1700

Data Index: 1422255 (Python Code)

Max Activating Token Index: 309

Text #7

Max Range: 4.4144. Min Range: -4.4144

Max Act: 4.2802. Min Act: -0.1700

Data Index: 799055 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 4.4144. Min Range: -4.4144

Max Act: 4.2854. Min Act: -0.1700

Data Index: 1613606 (Python Code)

Max Activating Token Index: 699

Text #9

Max Range: 4.4144. Min Range: -4.4144

Max Act: 4.3080. Min Act: -0.1700

Data Index: 865921 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 4.4144. Min Range: -4.4144

Max Act: 4.2969. Min Act: -0.1700

Data Index: 777894 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 4.4144. Min Range: -4.4144

Max Act: 4.3013. Min Act: -0.1700

Data Index: 1547113 (Python Code)

Max Activating Token Index: 890

Text #12

Max Range: 4.4144. Min Range: -4.4144

Max Act: 4.2758. Min Act: -0.1700

Data Index: 1508142 (Python Code)

Max Activating Token Index: 582

Text #13

Max Range: 4.4144. Min Range: -4.4144

Max Act: 4.2746. Min Act: -0.1700

Data Index: 603344 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 4.4144. Min Range: -4.4144

Max Act: 4.2335. Min Act: -0.1700

Data Index: 1482118 (Python Code)

Max Activating Token Index: 556

Text #15

Max Range: 4.4144. Min Range: -4.4144

Max Act: 4.2444. Min Act: -0.1700

Data Index: 1528990 (Python Code)

Max Activating Token Index: 1015

Text #16

Max Range: 4.4144. Min Range: -4.4144

Max Act: 4.2178. Min Act: -0.1700

Data Index: 860931 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 4.4144. Min Range: -4.4144

Max Act: 4.1785. Min Act: -0.1700

Data Index: 1362329 (Python Code)

Max Activating Token Index: 654

Text #18

Max Range: 4.4144. Min Range: -4.4144

Max Act: 4.2090. Min Act: -0.1700

Data Index: 1373013 (Python Code)

Max Activating Token Index: 1003

Text #19

Max Range: 4.4144. Min Range: -4.4144

Max Act: 4.1867. Min Act: -0.1700

Data Index: 172429 (C4 (Web Text))

Max Activating Token Index: 454