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

Dataset: Open Web Text

Neuron 2467 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: 4.5883. Min Range: -4.5883

Max Act: 4.5883. Min Act: -0.1700

Data Index: 7640077 (Open Web Text)

Max Activating Token Index: 475

Text #1

Max Range: 4.5883. Min Range: -4.5883

Max Act: 4.5167. Min Act: -0.1700

Data Index: 41100 (Open Web Text)

Max Activating Token Index: 466

Text #2

Max Range: 4.5883. Min Range: -4.5883

Max Act: 4.5449. Min Act: -0.1700

Data Index: 8015692 (Open Web Text)

Max Activating Token Index: 437

Text #3

Max Range: 4.5883. Min Range: -4.5883

Max Act: 4.4885. Min Act: -0.1700

Data Index: 5845856 (Open Web Text)

Max Activating Token Index: 497

Text #4

Max Range: 4.5883. Min Range: -4.5883

Max Act: 4.4805. Min Act: -0.1700

Data Index: 1111479 (Open Web Text)

Max Activating Token Index: 116

Text #5

Max Range: 4.5883. Min Range: -4.5883

Max Act: 4.4809. Min Act: -0.1700

Data Index: 6004604 (Open Web Text)

Max Activating Token Index: 445

Text #6

Max Range: 4.5883. Min Range: -4.5883

Max Act: 4.4794. Min Act: -0.1700

Data Index: 1660669 (Open Web Text)

Max Activating Token Index: 142

Text #7

Max Range: 4.5883. Min Range: -4.5883

Max Act: 4.4641. Min Act: -0.1700

Data Index: 1622395 (Open Web Text)

Max Activating Token Index: 137

Text #8

Max Range: 4.5883. Min Range: -4.5883

Max Act: 4.4431. Min Act: -0.1700

Data Index: 8719601 (Open Web Text)

Max Activating Token Index: 904

Text #9

Max Range: 4.5883. Min Range: -4.5883

Max Act: 4.4643. Min Act: -0.1700

Data Index: 1802818 (Open Web Text)

Max Activating Token Index: 848

Text #10

Max Range: 4.5883. Min Range: -4.5883

Max Act: 4.4578. Min Act: -0.1700

Data Index: 8603972 (Open Web Text)

Max Activating Token Index: 411

Text #11

Max Range: 4.5883. Min Range: -4.5883

Max Act: 4.4478. Min Act: -0.1700

Data Index: 8196754 (Open Web Text)

Max Activating Token Index: 418

Text #12

Max Range: 4.5883. Min Range: -4.5883

Max Act: 4.4659. Min Act: -0.1700

Data Index: 4417833 (Open Web Text)

Max Activating Token Index: 1010

Text #13

Max Range: 4.5883. Min Range: -4.5883

Max Act: 4.4413. Min Act: -0.1700

Data Index: 5501436 (Open Web Text)

Max Activating Token Index: 312

Text #14

Max Range: 4.5883. Min Range: -4.5883

Max Act: 4.4527. Min Act: -0.1700

Data Index: 6475243 (Open Web Text)

Max Activating Token Index: 524

Text #15

Max Range: 4.5883. Min Range: -4.5883

Max Act: 4.4493. Min Act: -0.1700

Data Index: 2922935 (Open Web Text)

Max Activating Token Index: 546

Text #16

Max Range: 4.5883. Min Range: -4.5883

Max Act: 4.4552. Min Act: -0.1700

Data Index: 6362410 (Open Web Text)

Max Activating Token Index: 521

Text #17

Max Range: 4.5883. Min Range: -4.5883

Max Act: 4.4570. Min Act: -0.1700

Data Index: 80818 (Open Web Text)

Max Activating Token Index: 110

Text #18

Max Range: 4.5883. Min Range: -4.5883

Max Act: 4.4710. Min Act: -0.1700

Data Index: 5962012 (Open Web Text)

Max Activating Token Index: 686

Text #19

Max Range: 4.5883. Min Range: -4.5883

Max Act: 4.4663. Min Act: -0.1700

Data Index: 5837901 (Open Web Text)

Max Activating Token Index: 432