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

Dataset: Open Web Text

Neuron 1893 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: 3.4803. Min Range: -3.4803

Max Act: 3.4803. Min Act: -0.1700

Data Index: 7686103 (Open Web Text)

Max Activating Token Index: 653

Text #1

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.3728. Min Act: -0.1700

Data Index: 4129625 (Open Web Text)

Max Activating Token Index: 687

Text #2

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.4125. Min Act: -0.1700

Data Index: 7264002 (Open Web Text)

Max Activating Token Index: 636

Text #3

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.3556. Min Act: -0.1700

Data Index: 7621717 (Open Web Text)

Max Activating Token Index: 837

Text #4

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.3449. Min Act: -0.1700

Data Index: 8015322 (Open Web Text)

Max Activating Token Index: 894

Text #5

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.3232. Min Act: -0.1700

Data Index: 6955924 (Open Web Text)

Max Activating Token Index: 389

Text #6

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.3076. Min Act: -0.1700

Data Index: 8185375 (Open Web Text)

Max Activating Token Index: 323

Text #7

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.2725. Min Act: -0.1700

Data Index: 5162605 (Open Web Text)

Max Activating Token Index: 640

Text #8

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.3023. Min Act: -0.1700

Data Index: 7868571 (Open Web Text)

Max Activating Token Index: 671

Text #9

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.2968. Min Act: -0.1700

Data Index: 7183129 (Open Web Text)

Max Activating Token Index: 795

Text #10

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.2818. Min Act: -0.1700

Data Index: 264492 (Open Web Text)

Max Activating Token Index: 98

Text #11

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.2450. Min Act: -0.1700

Data Index: 3042345 (Open Web Text)

Max Activating Token Index: 293

Text #12

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.2486. Min Act: -0.1700

Data Index: 3422520 (Open Web Text)

Max Activating Token Index: 302

Text #13

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.2480. Min Act: -0.1700

Data Index: 6107116 (Open Web Text)

Max Activating Token Index: 304

Text #14

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.2212. Min Act: -0.1700

Data Index: 985195 (Open Web Text)

Max Activating Token Index: 936

Text #15

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.1933. Min Act: -0.1700

Data Index: 8079533 (Open Web Text)

Max Activating Token Index: 949

Text #16

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.2439. Min Act: -0.1700

Data Index: 7421167 (Open Web Text)

Max Activating Token Index: 204

Text #17

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.2171. Min Act: -0.1700

Data Index: 7381032 (Open Web Text)

Max Activating Token Index: 1001

Text #18

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.2287. Min Act: -0.1700

Data Index: 2161421 (Open Web Text)

Max Activating Token Index: 601

Text #19

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.2211. Min Act: -0.1700

Data Index: 1747042 (Open Web Text)

Max Activating Token Index: 645