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

Dataset: Open Web Text

Neuron 1597 in Layer 4

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: 5.3050. Min Range: -5.3050

Max Act: 5.3050. Min Act: -0.1700

Data Index: 3110897 (Open Web Text)

Max Activating Token Index: 906

Text #1

Max Range: 5.3050. Min Range: -5.3050

Max Act: 5.2660. Min Act: -0.1700

Data Index: 7909333 (Open Web Text)

Max Activating Token Index: 785

Text #2

Max Range: 5.3050. Min Range: -5.3050

Max Act: 5.1189. Min Act: -0.1700

Data Index: 2628665 (Open Web Text)

Max Activating Token Index: 459

Text #3

Max Range: 5.3050. Min Range: -5.3050

Max Act: 5.2049. Min Act: -0.1700

Data Index: 262356 (Open Web Text)

Max Activating Token Index: 716

Text #4

Max Range: 5.3050. Min Range: -5.3050

Max Act: 5.0756. Min Act: -0.1700

Data Index: 7199448 (Open Web Text)

Max Activating Token Index: 939

Text #5

Max Range: 5.3050. Min Range: -5.3050

Max Act: 5.0735. Min Act: -0.1700

Data Index: 6071063 (Open Web Text)

Max Activating Token Index: 580

Text #6

Max Range: 5.3050. Min Range: -5.3050

Max Act: 5.1075. Min Act: -0.1700

Data Index: 8273197 (Open Web Text)

Max Activating Token Index: 928

Text #7

Max Range: 5.3050. Min Range: -5.3050

Max Act: 5.0196. Min Act: -0.1700

Data Index: 4507004 (Open Web Text)

Max Activating Token Index: 884

Text #8

Max Range: 5.3050. Min Range: -5.3050

Max Act: 5.0670. Min Act: -0.1700

Data Index: 8549417 (Open Web Text)

Max Activating Token Index: 480

Text #9

Max Range: 5.3050. Min Range: -5.3050

Max Act: 5.0006. Min Act: -0.1700

Data Index: 2543689 (Open Web Text)

Max Activating Token Index: 570

Text #10

Max Range: 5.3050. Min Range: -5.3050

Max Act: 5.0374. Min Act: -0.1700

Data Index: 5121631 (Open Web Text)

Max Activating Token Index: 944

Text #11

Max Range: 5.3050. Min Range: -5.3050

Max Act: 5.0346. Min Act: -0.1700

Data Index: 5582404 (Open Web Text)

Max Activating Token Index: 383

Text #12

Max Range: 5.3050. Min Range: -5.3050

Max Act: 5.0293. Min Act: -0.1700

Data Index: 7647913 (Open Web Text)

Max Activating Token Index: 236

Text #13

Max Range: 5.3050. Min Range: -5.3050

Max Act: 5.0247. Min Act: -0.1700

Data Index: 3288061 (Open Web Text)

Max Activating Token Index: 734

Text #14

Max Range: 5.3050. Min Range: -5.3050

Max Act: 5.0246. Min Act: -0.1700

Data Index: 5948993 (Open Web Text)

Max Activating Token Index: 491

Text #15

Max Range: 5.3050. Min Range: -5.3050

Max Act: 5.0216. Min Act: -0.1700

Data Index: 5970717 (Open Web Text)

Max Activating Token Index: 321

Text #16

Max Range: 5.3050. Min Range: -5.3050

Max Act: 5.0233. Min Act: -0.1700

Data Index: 3085836 (Open Web Text)

Max Activating Token Index: 407

Text #17

Max Range: 5.3050. Min Range: -5.3050

Max Act: 5.0334. Min Act: -0.1700

Data Index: 4372917 (Open Web Text)

Max Activating Token Index: 919

Text #18

Max Range: 5.3050. Min Range: -5.3050

Max Act: 5.0578. Min Act: -0.1700

Data Index: 2776756 (Open Web Text)

Max Activating Token Index: 670

Text #19

Max Range: 5.3050. Min Range: -5.3050

Max Act: 5.0247. Min Act: -0.1700

Data Index: 759816 (Open Web Text)

Max Activating Token Index: 582