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

Dataset: Open Web Text

Neuron 1551 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: 2.6521. Min Range: -2.6521

Max Act: 2.6521. Min Act: -0.1700

Data Index: 2454296 (Open Web Text)

Max Activating Token Index: 851

Text #1

Max Range: 2.6521. Min Range: -2.6521

Max Act: 2.6253. Min Act: -0.1700

Data Index: 3389065 (Open Web Text)

Max Activating Token Index: 115

Text #2

Max Range: 2.6521. Min Range: -2.6521

Max Act: 2.5801. Min Act: -0.1700

Data Index: 3792384 (Open Web Text)

Max Activating Token Index: 613

Text #3

Max Range: 2.6521. Min Range: -2.6521

Max Act: 2.5837. Min Act: -0.1700

Data Index: 7041904 (Open Web Text)

Max Activating Token Index: 663

Text #4

Max Range: 2.6521. Min Range: -2.6521

Max Act: 2.5727. Min Act: -0.1700

Data Index: 204802 (Open Web Text)

Max Activating Token Index: 405

Text #5

Max Range: 2.6521. Min Range: -2.6521

Max Act: 2.5538. Min Act: -0.1700

Data Index: 3256537 (Open Web Text)

Max Activating Token Index: 719

Text #6

Max Range: 2.6521. Min Range: -2.6521

Max Act: 2.5651. Min Act: -0.1700

Data Index: 7245507 (Open Web Text)

Max Activating Token Index: 510

Text #7

Max Range: 2.6521. Min Range: -2.6521

Max Act: 2.5601. Min Act: -0.1700

Data Index: 8408554 (Open Web Text)

Max Activating Token Index: 636

Text #8

Max Range: 2.6521. Min Range: -2.6521

Max Act: 2.5694. Min Act: -0.1700

Data Index: 1538931 (Open Web Text)

Max Activating Token Index: 99

Text #9

Max Range: 2.6521. Min Range: -2.6521

Max Act: 2.5346. Min Act: -0.1700

Data Index: 7518195 (Open Web Text)

Max Activating Token Index: 743

Text #10

Max Range: 2.6521. Min Range: -2.6521

Max Act: 2.5210. Min Act: -0.1700

Data Index: 7027525 (Open Web Text)

Max Activating Token Index: 642

Text #11

Max Range: 2.6521. Min Range: -2.6521

Max Act: 2.5286. Min Act: -0.1700

Data Index: 3170474 (Open Web Text)

Max Activating Token Index: 481

Text #12

Max Range: 2.6521. Min Range: -2.6521

Max Act: 2.5241. Min Act: -0.1700

Data Index: 541630 (Open Web Text)

Max Activating Token Index: 935

Text #13

Max Range: 2.6521. Min Range: -2.6521

Max Act: 2.5265. Min Act: -0.1700

Data Index: 8610690 (Open Web Text)

Max Activating Token Index: 491

Text #14

Max Range: 2.6521. Min Range: -2.6521

Max Act: 2.5028. Min Act: -0.1700

Data Index: 7367196 (Open Web Text)

Max Activating Token Index: 724

Text #15

Max Range: 2.6521. Min Range: -2.6521

Max Act: 2.5172. Min Act: -0.1700

Data Index: 7688061 (Open Web Text)

Max Activating Token Index: 514

Text #16

Max Range: 2.6521. Min Range: -2.6521

Max Act: 2.5056. Min Act: -0.1700

Data Index: 289852 (Open Web Text)

Max Activating Token Index: 701

Text #17

Max Range: 2.6521. Min Range: -2.6521

Max Act: 2.5027. Min Act: -0.1700

Data Index: 5837663 (Open Web Text)

Max Activating Token Index: 495

Text #18

Max Range: 2.6521. Min Range: -2.6521

Max Act: 2.5004. Min Act: -0.1700

Data Index: 1939868 (Open Web Text)

Max Activating Token Index: 444

Text #19

Max Range: 2.6521. Min Range: -2.6521

Max Act: 2.5160. Min Act: -0.1700

Data Index: 4160095 (Open Web Text)

Max Activating Token Index: 70