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

Dataset: Open Web Text

Neuron 1404 in Layer 5

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: 5.2870. Min Range: -5.2870

Max Act: 5.2870. Min Act: -0.1700

Data Index: 7829768 (Open Web Text)

Max Activating Token Index: 90

Text #1

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.2138. Min Act: -0.1700

Data Index: 6840956 (Open Web Text)

Max Activating Token Index: 296

Text #2

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.1668. Min Act: -0.1700

Data Index: 67818 (Open Web Text)

Max Activating Token Index: 569

Text #3

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.1467. Min Act: -0.1700

Data Index: 2953687 (Open Web Text)

Max Activating Token Index: 460

Text #4

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.1470. Min Act: -0.1700

Data Index: 4028845 (Open Web Text)

Max Activating Token Index: 162

Text #5

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.1641. Min Act: -0.1700

Data Index: 4167081 (Open Web Text)

Max Activating Token Index: 222

Text #6

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.1032. Min Act: -0.1700

Data Index: 352012 (Open Web Text)

Max Activating Token Index: 822

Text #7

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.1029. Min Act: -0.1700

Data Index: 6292910 (Open Web Text)

Max Activating Token Index: 827

Text #8

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.1036. Min Act: -0.1700

Data Index: 5846727 (Open Web Text)

Max Activating Token Index: 860

Text #9

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.1003. Min Act: -0.1700

Data Index: 961829 (Open Web Text)

Max Activating Token Index: 438

Text #10

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.0705. Min Act: -0.1700

Data Index: 2362113 (Open Web Text)

Max Activating Token Index: 248

Text #11

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.1278. Min Act: -0.1700

Data Index: 8535350 (Open Web Text)

Max Activating Token Index: 80

Text #12

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.1401. Min Act: -0.1700

Data Index: 2272967 (Open Web Text)

Max Activating Token Index: 948

Text #13

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.0923. Min Act: -0.1700

Data Index: 8632381 (Open Web Text)

Max Activating Token Index: 590

Text #14

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.0727. Min Act: -0.1700

Data Index: 8792190 (Open Web Text)

Max Activating Token Index: 1010

Text #15

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.1083. Min Act: -0.1700

Data Index: 8006041 (Open Web Text)

Max Activating Token Index: 227

Text #16

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.0791. Min Act: -0.1700

Data Index: 1647401 (Open Web Text)

Max Activating Token Index: 576

Text #17

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.0441. Min Act: -0.1700

Data Index: 1005915 (Open Web Text)

Max Activating Token Index: 559

Text #18

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.0455. Min Act: -0.1700

Data Index: 2632598 (Open Web Text)

Max Activating Token Index: 116

Text #19

Max Range: 5.2870. Min Range: -5.2870

Max Act: 5.0277. Min Act: -0.1700

Data Index: 1077833 (Open Web Text)

Max Activating Token Index: 213