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

Dataset: Open Web Text

Neuron 2169 in Layer 3

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: 4.0644. Min Range: -4.0644

Max Act: 4.0644. Min Act: -0.1700

Data Index: 8693038 (Open Web Text)

Max Activating Token Index: 236

Text #1

Max Range: 4.0644. Min Range: -4.0644

Max Act: 4.0293. Min Act: -0.1700

Data Index: 6601768 (Open Web Text)

Max Activating Token Index: 454

Text #2

Max Range: 4.0644. Min Range: -4.0644

Max Act: 3.9163. Min Act: -0.1700

Data Index: 8277883 (Open Web Text)

Max Activating Token Index: 764

Text #3

Max Range: 4.0644. Min Range: -4.0644

Max Act: 3.8930. Min Act: -0.1700

Data Index: 1187407 (Open Web Text)

Max Activating Token Index: 678

Text #4

Max Range: 4.0644. Min Range: -4.0644

Max Act: 3.8618. Min Act: -0.1700

Data Index: 1805357 (Open Web Text)

Max Activating Token Index: 344

Text #5

Max Range: 4.0644. Min Range: -4.0644

Max Act: 3.8488. Min Act: -0.1700

Data Index: 2376628 (Open Web Text)

Max Activating Token Index: 695

Text #6

Max Range: 4.0644. Min Range: -4.0644

Max Act: 3.8418. Min Act: -0.1700

Data Index: 8026977 (Open Web Text)

Max Activating Token Index: 818

Text #7

Max Range: 4.0644. Min Range: -4.0644

Max Act: 3.8364. Min Act: -0.1700

Data Index: 2219728 (Open Web Text)

Max Activating Token Index: 447

Text #8

Max Range: 4.0644. Min Range: -4.0644

Max Act: 3.8480. Min Act: -0.1700

Data Index: 5609470 (Open Web Text)

Max Activating Token Index: 521

Text #9

Max Range: 4.0644. Min Range: -4.0644

Max Act: 3.8145. Min Act: -0.1700

Data Index: 1127323 (Open Web Text)

Max Activating Token Index: 681

Text #10

Max Range: 4.0644. Min Range: -4.0644

Max Act: 3.8201. Min Act: -0.1700

Data Index: 1810563 (Open Web Text)

Max Activating Token Index: 74

Text #11

Max Range: 4.0644. Min Range: -4.0644

Max Act: 3.8123. Min Act: -0.1700

Data Index: 1357365 (Open Web Text)

Max Activating Token Index: 552

Text #12

Max Range: 4.0644. Min Range: -4.0644

Max Act: 3.8119. Min Act: -0.1700

Data Index: 6036918 (Open Web Text)

Max Activating Token Index: 32

Text #13

Max Range: 4.0644. Min Range: -4.0644

Max Act: 3.7944. Min Act: -0.1700

Data Index: 3770174 (Open Web Text)

Max Activating Token Index: 755

Text #14

Max Range: 4.0644. Min Range: -4.0644

Max Act: 3.8130. Min Act: -0.1700

Data Index: 54791 (Open Web Text)

Max Activating Token Index: 893

Text #15

Max Range: 4.0644. Min Range: -4.0644

Max Act: 3.7820. Min Act: -0.1700

Data Index: 3372025 (Open Web Text)

Max Activating Token Index: 975

Text #16

Max Range: 4.0644. Min Range: -4.0644

Max Act: 3.7712. Min Act: -0.1700

Data Index: 7839856 (Open Web Text)

Max Activating Token Index: 498

Text #17

Max Range: 4.0644. Min Range: -4.0644

Max Act: 3.7552. Min Act: -0.1700

Data Index: 4876065 (Open Web Text)

Max Activating Token Index: 333

Text #18

Max Range: 4.0644. Min Range: -4.0644

Max Act: 3.7420. Min Act: -0.1700

Data Index: 4071419 (Open Web Text)

Max Activating Token Index: 59

Text #19

Max Range: 4.0644. Min Range: -4.0644

Max Act: 3.7491. Min Act: -0.1700

Data Index: 3039752 (Open Web Text)

Max Activating Token Index: 732