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

Dataset: Open Web Text

Neuron 1417 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: 3.7606. Min Range: -3.7606

Max Act: 3.7606. Min Act: -0.1700

Data Index: 6101003 (Open Web Text)

Max Activating Token Index: 133

Text #1

Max Range: 3.7606. Min Range: -3.7606

Max Act: 3.7028. Min Act: -0.1700

Data Index: 8279324 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 3.7606. Min Range: -3.7606

Max Act: 3.6769. Min Act: -0.1700

Data Index: 6603507 (Open Web Text)

Max Activating Token Index: 891

Text #3

Max Range: 3.7606. Min Range: -3.7606

Max Act: 3.6601. Min Act: -0.1700

Data Index: 1127718 (Open Web Text)

Max Activating Token Index: 127

Text #4

Max Range: 3.7606. Min Range: -3.7606

Max Act: 3.6217. Min Act: -0.1700

Data Index: 1667893 (Open Web Text)

Max Activating Token Index: 465

Text #5

Max Range: 3.7606. Min Range: -3.7606

Max Act: 3.6440. Min Act: -0.1700

Data Index: 1339237 (Open Web Text)

Max Activating Token Index: 648

Text #6

Max Range: 3.7606. Min Range: -3.7606

Max Act: 3.6450. Min Act: -0.1700

Data Index: 6022003 (Open Web Text)

Max Activating Token Index: 176

Text #7

Max Range: 3.7606. Min Range: -3.7606

Max Act: 3.6159. Min Act: -0.1700

Data Index: 2097259 (Open Web Text)

Max Activating Token Index: 448

Text #8

Max Range: 3.7606. Min Range: -3.7606

Max Act: 3.6379. Min Act: -0.1700

Data Index: 4837114 (Open Web Text)

Max Activating Token Index: 665

Text #9

Max Range: 3.7606. Min Range: -3.7606

Max Act: 3.6217. Min Act: -0.1700

Data Index: 7277267 (Open Web Text)

Max Activating Token Index: 646

Text #10

Max Range: 3.7606. Min Range: -3.7606

Max Act: 3.6278. Min Act: -0.1700

Data Index: 7244795 (Open Web Text)

Max Activating Token Index: 516

Text #11

Max Range: 3.7606. Min Range: -3.7606

Max Act: 3.5895. Min Act: -0.1700

Data Index: 1857794 (Open Web Text)

Max Activating Token Index: 220

Text #12

Max Range: 3.7606. Min Range: -3.7606

Max Act: 3.5992. Min Act: -0.1700

Data Index: 968321 (Open Web Text)

Max Activating Token Index: 346

Text #13

Max Range: 3.7606. Min Range: -3.7606

Max Act: 3.5907. Min Act: -0.1700

Data Index: 4532867 (Open Web Text)

Max Activating Token Index: 75

Text #14

Max Range: 3.7606. Min Range: -3.7606

Max Act: 3.5746. Min Act: -0.1700

Data Index: 1895325 (Open Web Text)

Max Activating Token Index: 359

Text #15

Max Range: 3.7606. Min Range: -3.7606

Max Act: 3.5701. Min Act: -0.1700

Data Index: 4883390 (Open Web Text)

Max Activating Token Index: 979

Text #16

Max Range: 3.7606. Min Range: -3.7606

Max Act: 3.5833. Min Act: -0.1700

Data Index: 1275691 (Open Web Text)

Max Activating Token Index: 1019

Text #17

Max Range: 3.7606. Min Range: -3.7606

Max Act: 3.5896. Min Act: -0.1700

Data Index: 5219831 (Open Web Text)

Max Activating Token Index: 779

Text #18

Max Range: 3.7606. Min Range: -3.7606

Max Act: 3.5959. Min Act: -0.1700

Data Index: 5873870 (Open Web Text)

Max Activating Token Index: 443

Text #19

Max Range: 3.7606. Min Range: -3.7606

Max Act: 3.5899. Min Act: -0.1700

Data Index: 5905211 (Open Web Text)

Max Activating Token Index: 517