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

Dataset: Open Web Text

Neuron 1776 in Layer 1

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: 5.2688. Min Range: -5.2688

Max Act: 5.2688. Min Act: -0.1700

Data Index: 2458722 (Open Web Text)

Max Activating Token Index: 115

Text #1

Max Range: 5.2688. Min Range: -5.2688

Max Act: 5.1096. Min Act: -0.1700

Data Index: 2592940 (Open Web Text)

Max Activating Token Index: 102

Text #2

Max Range: 5.2688. Min Range: -5.2688

Max Act: 5.1059. Min Act: -0.1700

Data Index: 8055601 (Open Web Text)

Max Activating Token Index: 211

Text #3

Max Range: 5.2688. Min Range: -5.2688

Max Act: 4.9645. Min Act: -0.1698

Data Index: 8165914 (Open Web Text)

Max Activating Token Index: 173

Text #4

Max Range: 5.2688. Min Range: -5.2688

Max Act: 4.9455. Min Act: -0.1700

Data Index: 1132599 (Open Web Text)

Max Activating Token Index: 542

Text #5

Max Range: 5.2688. Min Range: -5.2688

Max Act: 4.8945. Min Act: -0.1700

Data Index: 2592943 (Open Web Text)

Max Activating Token Index: 297

Text #6

Max Range: 5.2688. Min Range: -5.2688

Max Act: 4.8963. Min Act: -0.1700

Data Index: 2100750 (Open Web Text)

Max Activating Token Index: 62

Text #7

Max Range: 5.2688. Min Range: -5.2688

Max Act: 4.9153. Min Act: -0.1700

Data Index: 2592949 (Open Web Text)

Max Activating Token Index: 530

Text #8

Max Range: 5.2688. Min Range: -5.2688

Max Act: 4.8697. Min Act: -0.1700

Data Index: 558121 (Open Web Text)

Max Activating Token Index: 155

Text #9

Max Range: 5.2688. Min Range: -5.2688

Max Act: 4.8548. Min Act: -0.1700

Data Index: 1729851 (Open Web Text)

Max Activating Token Index: 253

Text #10

Max Range: 5.2688. Min Range: -5.2688

Max Act: 4.8836. Min Act: -0.1700

Data Index: 2592941 (Open Web Text)

Max Activating Token Index: 481

Text #11

Max Range: 5.2688. Min Range: -5.2688

Max Act: 4.8152. Min Act: -0.1700

Data Index: 8399504 (Open Web Text)

Max Activating Token Index: 369

Text #12

Max Range: 5.2688. Min Range: -5.2688

Max Act: 4.8477. Min Act: -0.1700

Data Index: 2549793 (Open Web Text)

Max Activating Token Index: 288

Text #13

Max Range: 5.2688. Min Range: -5.2688

Max Act: 4.8201. Min Act: -0.1700

Data Index: 468161 (Open Web Text)

Max Activating Token Index: 240

Text #14

Max Range: 5.2688. Min Range: -5.2688

Max Act: 4.7637. Min Act: -0.1700

Data Index: 4272395 (Open Web Text)

Max Activating Token Index: 97

Text #15

Max Range: 5.2688. Min Range: -5.2688

Max Act: 4.7638. Min Act: -0.1700

Data Index: 4158179 (Open Web Text)

Max Activating Token Index: 302

Text #16

Max Range: 5.2688. Min Range: -5.2688

Max Act: 4.7933. Min Act: -0.1700

Data Index: 2808767 (Open Web Text)

Max Activating Token Index: 82

Text #17

Max Range: 5.2688. Min Range: -5.2688

Max Act: 4.8261. Min Act: -0.1700

Data Index: 4004730 (Open Web Text)

Max Activating Token Index: 863

Text #18

Max Range: 5.2688. Min Range: -5.2688

Max Act: 4.7661. Min Act: -0.1700

Data Index: 2592946 (Open Web Text)

Max Activating Token Index: 759

Text #19

Max Range: 5.2688. Min Range: -5.2688

Max Act: 4.7468. Min Act: -0.1700

Data Index: 4672815 (Open Web Text)

Max Activating Token Index: 773