Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 524 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.4897. Min Range: -4.4897

Max Act: 4.4897. Min Act: -0.1700

Data Index: 7026740 (Open Web Text)

Max Activating Token Index: 417

Text #1

Max Range: 4.4897. Min Range: -4.4897

Max Act: 4.4186. Min Act: -0.1700

Data Index: 6061636 (Open Web Text)

Max Activating Token Index: 483

Text #2

Max Range: 4.4897. Min Range: -4.4897

Max Act: 4.4520. Min Act: -0.1700

Data Index: 6180147 (Open Web Text)

Max Activating Token Index: 449

Text #3

Max Range: 4.4897. Min Range: -4.4897

Max Act: 4.4272. Min Act: -0.1700

Data Index: 4945780 (Open Web Text)

Max Activating Token Index: 759

Text #4

Max Range: 4.4897. Min Range: -4.4897

Max Act: 4.4104. Min Act: -0.1700

Data Index: 4277383 (Open Web Text)

Max Activating Token Index: 448

Text #5

Max Range: 4.4897. Min Range: -4.4897

Max Act: 4.3787. Min Act: -0.1700

Data Index: 2584599 (Open Web Text)

Max Activating Token Index: 173

Text #6

Max Range: 4.4897. Min Range: -4.4897

Max Act: 4.3709. Min Act: -0.1700

Data Index: 6247127 (Open Web Text)

Max Activating Token Index: 63

Text #7

Max Range: 4.4897. Min Range: -4.4897

Max Act: 4.3780. Min Act: -0.1700

Data Index: 1735870 (Open Web Text)

Max Activating Token Index: 663

Text #8

Max Range: 4.4897. Min Range: -4.4897

Max Act: 4.3798. Min Act: -0.1700

Data Index: 711926 (Open Web Text)

Max Activating Token Index: 824

Text #9

Max Range: 4.4897. Min Range: -4.4897

Max Act: 4.3393. Min Act: -0.1700

Data Index: 8505730 (Open Web Text)

Max Activating Token Index: 843

Text #10

Max Range: 4.4897. Min Range: -4.4897

Max Act: 4.3698. Min Act: -0.1700

Data Index: 4208432 (Open Web Text)

Max Activating Token Index: 590

Text #11

Max Range: 4.4897. Min Range: -4.4897

Max Act: 4.3659. Min Act: -0.1700

Data Index: 1614111 (Open Web Text)

Max Activating Token Index: 696

Text #12

Max Range: 4.4897. Min Range: -4.4897

Max Act: 4.3147. Min Act: -0.1700

Data Index: 4499623 (Open Web Text)

Max Activating Token Index: 381

Text #13

Max Range: 4.4897. Min Range: -4.4897

Max Act: 4.3310. Min Act: -0.1700

Data Index: 2755688 (Open Web Text)

Max Activating Token Index: 780

Text #14

Max Range: 4.4897. Min Range: -4.4897

Max Act: 4.3255. Min Act: -0.1700

Data Index: 6871869 (Open Web Text)

Max Activating Token Index: 503

Text #15

Max Range: 4.4897. Min Range: -4.4897

Max Act: 4.2865. Min Act: -0.1700

Data Index: 2344403 (Open Web Text)

Max Activating Token Index: 704

Text #16

Max Range: 4.4897. Min Range: -4.4897

Max Act: 4.3027. Min Act: -0.1700

Data Index: 7747621 (Open Web Text)

Max Activating Token Index: 843

Text #17

Max Range: 4.4897. Min Range: -4.4897

Max Act: 4.2761. Min Act: -0.1700

Data Index: 2137137 (Open Web Text)

Max Activating Token Index: 1015

Text #18

Max Range: 4.4897. Min Range: -4.4897

Max Act: 4.2847. Min Act: -0.1700

Data Index: 2154125 (Open Web Text)

Max Activating Token Index: 988

Text #19

Max Range: 4.4897. Min Range: -4.4897

Max Act: 4.2390. Min Act: -0.1700

Data Index: 5853019 (Open Web Text)

Max Activating Token Index: 913