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

Dataset: Open Web Text

Neuron 1661 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: 4.6628. Min Range: -4.6628

Max Act: 4.6628. Min Act: -0.1700

Data Index: 2578893 (Open Web Text)

Max Activating Token Index: 551

Text #1

Max Range: 4.6628. Min Range: -4.6628

Max Act: 4.5491. Min Act: -0.1700

Data Index: 6313443 (Open Web Text)

Max Activating Token Index: 389

Text #2

Max Range: 4.6628. Min Range: -4.6628

Max Act: 4.5280. Min Act: -0.1700

Data Index: 3433774 (Open Web Text)

Max Activating Token Index: 534

Text #3

Max Range: 4.6628. Min Range: -4.6628

Max Act: 4.4796. Min Act: -0.1700

Data Index: 2362123 (Open Web Text)

Max Activating Token Index: 595

Text #4

Max Range: 4.6628. Min Range: -4.6628

Max Act: 4.4154. Min Act: -0.1700

Data Index: 491461 (Open Web Text)

Max Activating Token Index: 134

Text #5

Max Range: 4.6628. Min Range: -4.6628

Max Act: 4.3215. Min Act: -0.1700

Data Index: 1268760 (Open Web Text)

Max Activating Token Index: 92

Text #6

Max Range: 4.6628. Min Range: -4.6628

Max Act: 4.2925. Min Act: -0.1700

Data Index: 7227125 (Open Web Text)

Max Activating Token Index: 568

Text #7

Max Range: 4.6628. Min Range: -4.6628

Max Act: 4.2248. Min Act: -0.1700

Data Index: 4680335 (Open Web Text)

Max Activating Token Index: 899

Text #8

Max Range: 4.6628. Min Range: -4.6628

Max Act: 4.2437. Min Act: -0.1700

Data Index: 8370795 (Open Web Text)

Max Activating Token Index: 49

Text #9

Max Range: 4.6628. Min Range: -4.6628

Max Act: 4.2378. Min Act: -0.1700

Data Index: 8264652 (Open Web Text)

Max Activating Token Index: 408

Text #10

Max Range: 4.6628. Min Range: -4.6628

Max Act: 4.2358. Min Act: -0.1700

Data Index: 6766500 (Open Web Text)

Max Activating Token Index: 977

Text #11

Max Range: 4.6628. Min Range: -4.6628

Max Act: 4.2013. Min Act: -0.1700

Data Index: 476853 (Open Web Text)

Max Activating Token Index: 85

Text #12

Max Range: 4.6628. Min Range: -4.6628

Max Act: 4.1963. Min Act: -0.1700

Data Index: 3402205 (Open Web Text)

Max Activating Token Index: 284

Text #13

Max Range: 4.6628. Min Range: -4.6628

Max Act: 4.2026. Min Act: -0.1700

Data Index: 6674538 (Open Web Text)

Max Activating Token Index: 698

Text #14

Max Range: 4.6628. Min Range: -4.6628

Max Act: 4.1619. Min Act: -0.1700

Data Index: 1968226 (Open Web Text)

Max Activating Token Index: 564

Text #15

Max Range: 4.6628. Min Range: -4.6628

Max Act: 4.1507. Min Act: -0.1700

Data Index: 7461017 (Open Web Text)

Max Activating Token Index: 652

Text #16

Max Range: 4.6628. Min Range: -4.6628

Max Act: 4.1278. Min Act: -0.1700

Data Index: 6111663 (Open Web Text)

Max Activating Token Index: 656

Text #17

Max Range: 4.6628. Min Range: -4.6628

Max Act: 4.0984. Min Act: -0.1700

Data Index: 4574164 (Open Web Text)

Max Activating Token Index: 982

Text #18

Max Range: 4.6628. Min Range: -4.6628

Max Act: 4.1009. Min Act: -0.1700

Data Index: 1903827 (Open Web Text)

Max Activating Token Index: 623

Text #19

Max Range: 4.6628. Min Range: -4.6628

Max Act: 4.0720. Min Act: -0.1700

Data Index: 7700567 (Open Web Text)

Max Activating Token Index: 517