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

Dataset: Open Web Text

Neuron 2141 in Layer 1

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: 6.0631. Min Range: -6.0631

Max Act: 6.0631. Min Act: -0.1700

Data Index: 1027918 (Open Web Text)

Max Activating Token Index: 925

Text #1

Max Range: 6.0631. Min Range: -6.0631

Max Act: 5.9391. Min Act: -0.1700

Data Index: 3294767 (Open Web Text)

Max Activating Token Index: 400

Text #2

Max Range: 6.0631. Min Range: -6.0631

Max Act: 5.9387. Min Act: -0.1700

Data Index: 4852257 (Open Web Text)

Max Activating Token Index: 611

Text #3

Max Range: 6.0631. Min Range: -6.0631

Max Act: 5.9032. Min Act: -0.1700

Data Index: 7441174 (Open Web Text)

Max Activating Token Index: 439

Text #4

Max Range: 6.0631. Min Range: -6.0631

Max Act: 5.8837. Min Act: -0.1700

Data Index: 3864206 (Open Web Text)

Max Activating Token Index: 573

Text #5

Max Range: 6.0631. Min Range: -6.0631

Max Act: 5.8498. Min Act: -0.1700

Data Index: 5011796 (Open Web Text)

Max Activating Token Index: 223

Text #6

Max Range: 6.0631. Min Range: -6.0631

Max Act: 5.8663. Min Act: -0.1700

Data Index: 5683627 (Open Web Text)

Max Activating Token Index: 217

Text #7

Max Range: 6.0631. Min Range: -6.0631

Max Act: 5.8163. Min Act: -0.1700

Data Index: 8649384 (Open Web Text)

Max Activating Token Index: 206

Text #8

Max Range: 6.0631. Min Range: -6.0631

Max Act: 5.7838. Min Act: -0.1700

Data Index: 4553432 (Open Web Text)

Max Activating Token Index: 323

Text #9

Max Range: 6.0631. Min Range: -6.0631

Max Act: 5.8099. Min Act: -0.1700

Data Index: 3103402 (Open Web Text)

Max Activating Token Index: 640

Text #10

Max Range: 6.0631. Min Range: -6.0631

Max Act: 5.8381. Min Act: -0.1700

Data Index: 4528066 (Open Web Text)

Max Activating Token Index: 535

Text #11

Max Range: 6.0631. Min Range: -6.0631

Max Act: 5.7828. Min Act: -0.1700

Data Index: 7578646 (Open Web Text)

Max Activating Token Index: 922

Text #12

Max Range: 6.0631. Min Range: -6.0631

Max Act: 5.7733. Min Act: -0.1700

Data Index: 6261460 (Open Web Text)

Max Activating Token Index: 658

Text #13

Max Range: 6.0631. Min Range: -6.0631

Max Act: 5.7585. Min Act: -0.1700

Data Index: 774339 (Open Web Text)

Max Activating Token Index: 345

Text #14

Max Range: 6.0631. Min Range: -6.0631

Max Act: 5.7757. Min Act: -0.1700

Data Index: 7029260 (Open Web Text)

Max Activating Token Index: 585

Text #15

Max Range: 6.0631. Min Range: -6.0631

Max Act: 5.7363. Min Act: -0.1700

Data Index: 3103417 (Open Web Text)

Max Activating Token Index: 68

Text #16

Max Range: 6.0631. Min Range: -6.0631

Max Act: 5.7525. Min Act: -0.1700

Data Index: 5324953 (Open Web Text)

Max Activating Token Index: 162

Text #17

Max Range: 6.0631. Min Range: -6.0631

Max Act: 5.7243. Min Act: -0.1700

Data Index: 945620 (Open Web Text)

Max Activating Token Index: 760

Text #18

Max Range: 6.0631. Min Range: -6.0631

Max Act: 5.7409. Min Act: -0.1700

Data Index: 1809121 (Open Web Text)

Max Activating Token Index: 214

Text #19

Max Range: 6.0631. Min Range: -6.0631

Max Act: 5.7390. Min Act: -0.1700

Data Index: 2470066 (Open Web Text)

Max Activating Token Index: 77