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

Dataset: Open Web Text

Neuron 1420 in Layer 6

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: 5.3615. Min Range: -5.3615

Max Act: 5.3615. Min Act: -0.1700

Data Index: 1645100 (Open Web Text)

Max Activating Token Index: 276

Text #1

Max Range: 5.3615. Min Range: -5.3615

Max Act: 5.2502. Min Act: -0.1700

Data Index: 6593401 (Open Web Text)

Max Activating Token Index: 583

Text #2

Max Range: 5.3615. Min Range: -5.3615

Max Act: 4.9828. Min Act: -0.1700

Data Index: 2485502 (Open Web Text)

Max Activating Token Index: 722

Text #3

Max Range: 5.3615. Min Range: -5.3615

Max Act: 4.9728. Min Act: -0.1700

Data Index: 6329528 (Open Web Text)

Max Activating Token Index: 722

Text #4

Max Range: 5.3615. Min Range: -5.3615

Max Act: 4.9628. Min Act: -0.1700

Data Index: 3747820 (Open Web Text)

Max Activating Token Index: 416

Text #5

Max Range: 5.3615. Min Range: -5.3615

Max Act: 4.9132. Min Act: -0.1700

Data Index: 2111137 (Open Web Text)

Max Activating Token Index: 669

Text #6

Max Range: 5.3615. Min Range: -5.3615

Max Act: 4.8970. Min Act: -0.1700

Data Index: 7692320 (Open Web Text)

Max Activating Token Index: 184

Text #7

Max Range: 5.3615. Min Range: -5.3615

Max Act: 4.9167. Min Act: -0.1700

Data Index: 7881346 (Open Web Text)

Max Activating Token Index: 371

Text #8

Max Range: 5.3615. Min Range: -5.3615

Max Act: 4.8939. Min Act: -0.1700

Data Index: 5116841 (Open Web Text)

Max Activating Token Index: 352

Text #9

Max Range: 5.3615. Min Range: -5.3615

Max Act: 4.8420. Min Act: -0.1700

Data Index: 7069897 (Open Web Text)

Max Activating Token Index: 995

Text #10

Max Range: 5.3615. Min Range: -5.3615

Max Act: 4.7768. Min Act: -0.1700

Data Index: 3325596 (Open Web Text)

Max Activating Token Index: 595

Text #11

Max Range: 5.3615. Min Range: -5.3615

Max Act: 4.8522. Min Act: -0.1700

Data Index: 7705659 (Open Web Text)

Max Activating Token Index: 715

Text #12

Max Range: 5.3615. Min Range: -5.3615

Max Act: 4.8296. Min Act: -0.1700

Data Index: 5303085 (Open Web Text)

Max Activating Token Index: 49

Text #13

Max Range: 5.3615. Min Range: -5.3615

Max Act: 4.7572. Min Act: -0.1700

Data Index: 4794353 (Open Web Text)

Max Activating Token Index: 861

Text #14

Max Range: 5.3615. Min Range: -5.3615

Max Act: 4.8071. Min Act: -0.1700

Data Index: 8022902 (Open Web Text)

Max Activating Token Index: 43

Text #15

Max Range: 5.3615. Min Range: -5.3615

Max Act: 4.8119. Min Act: -0.1700

Data Index: 1418572 (Open Web Text)

Max Activating Token Index: 819

Text #16

Max Range: 5.3615. Min Range: -5.3615

Max Act: 4.7673. Min Act: -0.1700

Data Index: 5186130 (Open Web Text)

Max Activating Token Index: 321

Text #17

Max Range: 5.3615. Min Range: -5.3615

Max Act: 4.8382. Min Act: -0.1700

Data Index: 6502634 (Open Web Text)

Max Activating Token Index: 222

Text #18

Max Range: 5.3615. Min Range: -5.3615

Max Act: 4.8149. Min Act: -0.1700

Data Index: 3165477 (Open Web Text)

Max Activating Token Index: 1001

Text #19

Max Range: 5.3615. Min Range: -5.3615

Max Act: 4.7725. Min Act: -0.1700

Data Index: 405609 (Open Web Text)

Max Activating Token Index: 26