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

Dataset: Open Web Text

Neuron 1714 in Layer 2

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: 3.1005. Min Range: -3.1005

Max Act: 3.1005. Min Act: -0.1700

Data Index: 7235239 (Open Web Text)

Max Activating Token Index: 280

Text #1

Max Range: 3.1005. Min Range: -3.1005

Max Act: 3.0683. Min Act: -0.1700

Data Index: 8503909 (Open Web Text)

Max Activating Token Index: 507

Text #2

Max Range: 3.1005. Min Range: -3.1005

Max Act: 3.0349. Min Act: -0.1700

Data Index: 5063211 (Open Web Text)

Max Activating Token Index: 168

Text #3

Max Range: 3.1005. Min Range: -3.1005

Max Act: 3.0491. Min Act: -0.1700

Data Index: 249012 (Open Web Text)

Max Activating Token Index: 758

Text #4

Max Range: 3.1005. Min Range: -3.1005

Max Act: 3.0432. Min Act: -0.1700

Data Index: 708347 (Open Web Text)

Max Activating Token Index: 326

Text #5

Max Range: 3.1005. Min Range: -3.1005

Max Act: 3.0215. Min Act: -0.1700

Data Index: 7174312 (Open Web Text)

Max Activating Token Index: 74

Text #6

Max Range: 3.1005. Min Range: -3.1005

Max Act: 3.0066. Min Act: -0.1700

Data Index: 999669 (Open Web Text)

Max Activating Token Index: 438

Text #7

Max Range: 3.1005. Min Range: -3.1005

Max Act: 3.0147. Min Act: -0.1700

Data Index: 3110777 (Open Web Text)

Max Activating Token Index: 772

Text #8

Max Range: 3.1005. Min Range: -3.1005

Max Act: 3.0009. Min Act: -0.1700

Data Index: 1089011 (Open Web Text)

Max Activating Token Index: 30

Text #9

Max Range: 3.1005. Min Range: -3.1005

Max Act: 2.9806. Min Act: -0.1700

Data Index: 7776287 (Open Web Text)

Max Activating Token Index: 192

Text #10

Max Range: 3.1005. Min Range: -3.1005

Max Act: 2.9876. Min Act: -0.1700

Data Index: 6099955 (Open Web Text)

Max Activating Token Index: 222

Text #11

Max Range: 3.1005. Min Range: -3.1005

Max Act: 2.9756. Min Act: -0.1700

Data Index: 1182114 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 3.1005. Min Range: -3.1005

Max Act: 2.9709. Min Act: -0.1700

Data Index: 4325450 (Open Web Text)

Max Activating Token Index: 80

Text #13

Max Range: 3.1005. Min Range: -3.1005

Max Act: 2.9767. Min Act: -0.1700

Data Index: 3335763 (Open Web Text)

Max Activating Token Index: 162

Text #14

Max Range: 3.1005. Min Range: -3.1005

Max Act: 2.9562. Min Act: -0.1700

Data Index: 2566207 (Open Web Text)

Max Activating Token Index: 246

Text #15

Max Range: 3.1005. Min Range: -3.1005

Max Act: 2.9525. Min Act: -0.1700

Data Index: 4386028 (Open Web Text)

Max Activating Token Index: 813

Text #16

Max Range: 3.1005. Min Range: -3.1005

Max Act: 2.9517. Min Act: -0.1700

Data Index: 2579677 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 3.1005. Min Range: -3.1005

Max Act: 2.9491. Min Act: -0.1700

Data Index: 5850682 (Open Web Text)

Max Activating Token Index: 498

Text #18

Max Range: 3.1005. Min Range: -3.1005

Max Act: 2.9452. Min Act: -0.1700

Data Index: 328381 (Open Web Text)

Max Activating Token Index: 312

Text #19

Max Range: 3.1005. Min Range: -3.1005

Max Act: 2.9455. Min Act: -0.1700

Data Index: 1651900 (Open Web Text)

Max Activating Token Index: 197