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

Dataset: Open Web Text

Neuron 2528 in Layer 0

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: 3.4032. Min Range: -3.4032

Max Act: 3.4032. Min Act: -0.1700

Data Index: 5503815 (Open Web Text)

Max Activating Token Index: 456

Text #1

Max Range: 3.4032. Min Range: -3.4032

Max Act: 3.3207. Min Act: -0.1700

Data Index: 6360312 (Open Web Text)

Max Activating Token Index: 920

Text #2

Max Range: 3.4032. Min Range: -3.4032

Max Act: 3.2859. Min Act: -0.1700

Data Index: 5963109 (Open Web Text)

Max Activating Token Index: 40

Text #3

Max Range: 3.4032. Min Range: -3.4032

Max Act: 3.2641. Min Act: -0.1700

Data Index: 1331793 (Open Web Text)

Max Activating Token Index: 291

Text #4

Max Range: 3.4032. Min Range: -3.4032

Max Act: 3.2483. Min Act: -0.1700

Data Index: 928253 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 3.4032. Min Range: -3.4032

Max Act: 3.2608. Min Act: -0.1700

Data Index: 7741562 (Open Web Text)

Max Activating Token Index: 17

Text #6

Max Range: 3.4032. Min Range: -3.4032

Max Act: 3.2545. Min Act: -0.1700

Data Index: 3000904 (Open Web Text)

Max Activating Token Index: 809

Text #7

Max Range: 3.4032. Min Range: -3.4032

Max Act: 3.2282. Min Act: -0.1700

Data Index: 6971409 (Open Web Text)

Max Activating Token Index: 306

Text #8

Max Range: 3.4032. Min Range: -3.4032

Max Act: 3.2067. Min Act: -0.1700

Data Index: 3483168 (Open Web Text)

Max Activating Token Index: 223

Text #9

Max Range: 3.4032. Min Range: -3.4032

Max Act: 3.2020. Min Act: -0.1700

Data Index: 3345746 (Open Web Text)

Max Activating Token Index: 45

Text #10

Max Range: 3.4032. Min Range: -3.4032

Max Act: 3.1988. Min Act: -0.1700

Data Index: 4388767 (Open Web Text)

Max Activating Token Index: 318

Text #11

Max Range: 3.4032. Min Range: -3.4032

Max Act: 3.2063. Min Act: -0.1700

Data Index: 7521984 (Open Web Text)

Max Activating Token Index: 389

Text #12

Max Range: 3.4032. Min Range: -3.4032

Max Act: 3.2026. Min Act: -0.1700

Data Index: 3561207 (Open Web Text)

Max Activating Token Index: 939

Text #13

Max Range: 3.4032. Min Range: -3.4032

Max Act: 3.2239. Min Act: -0.1700

Data Index: 1319277 (Open Web Text)

Max Activating Token Index: 307

Text #14

Max Range: 3.4032. Min Range: -3.4032

Max Act: 3.2139. Min Act: -0.1700

Data Index: 4364286 (Open Web Text)

Max Activating Token Index: 948

Text #15

Max Range: 3.4032. Min Range: -3.4032

Max Act: 3.2181. Min Act: -0.1700

Data Index: 7852545 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.4032. Min Range: -3.4032

Max Act: 3.1776. Min Act: -0.1700

Data Index: 8041482 (Open Web Text)

Max Activating Token Index: 668

Text #17

Max Range: 3.4032. Min Range: -3.4032

Max Act: 3.2023. Min Act: -0.1700

Data Index: 7989728 (Open Web Text)

Max Activating Token Index: 628

Text #18

Max Range: 3.4032. Min Range: -3.4032

Max Act: 3.1874. Min Act: -0.1700

Data Index: 588342 (Open Web Text)

Max Activating Token Index: 1021

Text #19

Max Range: 3.4032. Min Range: -3.4032

Max Act: 3.1977. Min Act: -0.1700

Data Index: 7584645 (Open Web Text)

Max Activating Token Index: 588