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

Dataset: Open Web Text

Neuron 148 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: 1.5492. Min Range: -1.5492

Max Act: 1.5492. Min Act: -0.1700

Data Index: 754206 (Open Web Text)

Max Activating Token Index: 483

Text #1

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.5106. Min Act: -0.1700

Data Index: 1143568 (Open Web Text)

Max Activating Token Index: 338

Text #2

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.4859. Min Act: -0.1700

Data Index: 6465795 (Open Web Text)

Max Activating Token Index: 438

Text #3

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.4765. Min Act: -0.1700

Data Index: 961156 (Open Web Text)

Max Activating Token Index: 381

Text #4

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.4722. Min Act: -0.1700

Data Index: 6806181 (Open Web Text)

Max Activating Token Index: 516

Text #5

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.4671. Min Act: -0.1700

Data Index: 7841112 (Open Web Text)

Max Activating Token Index: 534

Text #6

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.4480. Min Act: -0.1700

Data Index: 5076867 (Open Web Text)

Max Activating Token Index: 591

Text #7

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.4509. Min Act: -0.1700

Data Index: 6078125 (Open Web Text)

Max Activating Token Index: 308

Text #8

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.4462. Min Act: -0.1700

Data Index: 3719893 (Open Web Text)

Max Activating Token Index: 598

Text #9

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.4502. Min Act: -0.1700

Data Index: 7975098 (Open Web Text)

Max Activating Token Index: 537

Text #10

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.4385. Min Act: -0.1700

Data Index: 2411205 (Open Web Text)

Max Activating Token Index: 247

Text #11

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.4378. Min Act: -0.1700

Data Index: 7841113 (Open Web Text)

Max Activating Token Index: 462

Text #12

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.4372. Min Act: -0.1700

Data Index: 939714 (Open Web Text)

Max Activating Token Index: 583

Text #13

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.4315. Min Act: -0.1700

Data Index: 6072875 (Open Web Text)

Max Activating Token Index: 703

Text #14

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.4251. Min Act: -0.1699

Data Index: 796818 (Open Web Text)

Max Activating Token Index: 559

Text #15

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.4178. Min Act: -0.1700

Data Index: 1770153 (Open Web Text)

Max Activating Token Index: 750

Text #16

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.4281. Min Act: -0.1700

Data Index: 1969431 (Open Web Text)

Max Activating Token Index: 774

Text #17

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.4241. Min Act: -0.1700

Data Index: 7083907 (Open Web Text)

Max Activating Token Index: 265

Text #18

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.4295. Min Act: -0.1700

Data Index: 2710738 (Open Web Text)

Max Activating Token Index: 485

Text #19

Max Range: 1.5492. Min Range: -1.5492

Max Act: 1.4237. Min Act: -0.1700

Data Index: 3246523 (Open Web Text)

Max Activating Token Index: 749