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

Dataset: Open Web Text

Neuron 404 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: 3.8413. Min Range: -3.8413

Max Act: 3.8413. Min Act: -0.1700

Data Index: 6031943 (Open Web Text)

Max Activating Token Index: 400

Text #1

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.7547. Min Act: -0.1700

Data Index: 1955020 (Open Web Text)

Max Activating Token Index: 318

Text #2

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.7361. Min Act: -0.1700

Data Index: 7214447 (Open Web Text)

Max Activating Token Index: 249

Text #3

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6857. Min Act: -0.1700

Data Index: 6558270 (Open Web Text)

Max Activating Token Index: 734

Text #4

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.7281. Min Act: -0.1700

Data Index: 3048973 (Open Web Text)

Max Activating Token Index: 560

Text #5

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6750. Min Act: -0.1700

Data Index: 4850279 (Open Web Text)

Max Activating Token Index: 273

Text #6

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6194. Min Act: -0.1700

Data Index: 5070838 (Open Web Text)

Max Activating Token Index: 797

Text #7

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6516. Min Act: -0.1700

Data Index: 618864 (Open Web Text)

Max Activating Token Index: 370

Text #8

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6504. Min Act: -0.1700

Data Index: 1159939 (Open Web Text)

Max Activating Token Index: 122

Text #9

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6634. Min Act: -0.1700

Data Index: 7195743 (Open Web Text)

Max Activating Token Index: 734

Text #10

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6371. Min Act: -0.1700

Data Index: 3751141 (Open Web Text)

Max Activating Token Index: 845

Text #11

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6103. Min Act: -0.1700

Data Index: 3458076 (Open Web Text)

Max Activating Token Index: 500

Text #12

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6487. Min Act: -0.1700

Data Index: 3943123 (Open Web Text)

Max Activating Token Index: 842

Text #13

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6274. Min Act: -0.1700

Data Index: 2738214 (Open Web Text)

Max Activating Token Index: 566

Text #14

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6334. Min Act: -0.1700

Data Index: 4183298 (Open Web Text)

Max Activating Token Index: 658

Text #15

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6377. Min Act: -0.1700

Data Index: 5381007 (Open Web Text)

Max Activating Token Index: 618

Text #16

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6458. Min Act: -0.1700

Data Index: 4376023 (Open Web Text)

Max Activating Token Index: 593

Text #17

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6134. Min Act: -0.1700

Data Index: 4376022 (Open Web Text)

Max Activating Token Index: 1000

Text #18

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6109. Min Act: -0.1700

Data Index: 1382844 (Open Web Text)

Max Activating Token Index: 420

Text #19

Max Range: 3.8413. Min Range: -3.8413

Max Act: 3.6056. Min Act: -0.1700

Data Index: 3020064 (Open Web Text)

Max Activating Token Index: 775