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

Dataset: Open Web Text

Neuron 1154 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: 4.2294. Min Range: -4.2294

Max Act: 4.2294. Min Act: -0.1700

Data Index: 6204160 (Open Web Text)

Max Activating Token Index: 563

Text #1

Max Range: 4.2294. Min Range: -4.2294

Max Act: 4.1944. Min Act: -0.1700

Data Index: 7041317 (Open Web Text)

Max Activating Token Index: 492

Text #2

Max Range: 4.2294. Min Range: -4.2294

Max Act: 4.1808. Min Act: -0.1700

Data Index: 3156132 (Open Web Text)

Max Activating Token Index: 650

Text #3

Max Range: 4.2294. Min Range: -4.2294

Max Act: 4.0323. Min Act: -0.1700

Data Index: 3743096 (Open Web Text)

Max Activating Token Index: 772

Text #4

Max Range: 4.2294. Min Range: -4.2294

Max Act: 4.0568. Min Act: -0.1700

Data Index: 2338827 (Open Web Text)

Max Activating Token Index: 639

Text #5

Max Range: 4.2294. Min Range: -4.2294

Max Act: 4.0031. Min Act: -0.1700

Data Index: 1080727 (Open Web Text)

Max Activating Token Index: 605

Text #6

Max Range: 4.2294. Min Range: -4.2294

Max Act: 4.0669. Min Act: -0.1700

Data Index: 1221617 (Open Web Text)

Max Activating Token Index: 556

Text #7

Max Range: 4.2294. Min Range: -4.2294

Max Act: 4.0145. Min Act: -0.1700

Data Index: 1073025 (Open Web Text)

Max Activating Token Index: 148

Text #8

Max Range: 4.2294. Min Range: -4.2294

Max Act: 4.0080. Min Act: -0.1700

Data Index: 8474320 (Open Web Text)

Max Activating Token Index: 460

Text #9

Max Range: 4.2294. Min Range: -4.2294

Max Act: 3.9904. Min Act: -0.1700

Data Index: 5537311 (Open Web Text)

Max Activating Token Index: 560

Text #10

Max Range: 4.2294. Min Range: -4.2294

Max Act: 4.0519. Min Act: -0.1700

Data Index: 2600403 (Open Web Text)

Max Activating Token Index: 882

Text #11

Max Range: 4.2294. Min Range: -4.2294

Max Act: 4.0097. Min Act: -0.1700

Data Index: 1982931 (Open Web Text)

Max Activating Token Index: 445

Text #12

Max Range: 4.2294. Min Range: -4.2294

Max Act: 3.9838. Min Act: -0.1700

Data Index: 2126254 (Open Web Text)

Max Activating Token Index: 620

Text #13

Max Range: 4.2294. Min Range: -4.2294

Max Act: 4.0051. Min Act: -0.1700

Data Index: 3179330 (Open Web Text)

Max Activating Token Index: 905

Text #14

Max Range: 4.2294. Min Range: -4.2294

Max Act: 3.9555. Min Act: -0.1700

Data Index: 3261548 (Open Web Text)

Max Activating Token Index: 363

Text #15

Max Range: 4.2294. Min Range: -4.2294

Max Act: 3.9596. Min Act: -0.1700

Data Index: 721470 (Open Web Text)

Max Activating Token Index: 572

Text #16

Max Range: 4.2294. Min Range: -4.2294

Max Act: 3.9565. Min Act: -0.1700

Data Index: 8050456 (Open Web Text)

Max Activating Token Index: 574

Text #17

Max Range: 4.2294. Min Range: -4.2294

Max Act: 4.0743. Min Act: -0.1700

Data Index: 8170034 (Open Web Text)

Max Activating Token Index: 648

Text #18

Max Range: 4.2294. Min Range: -4.2294

Max Act: 4.0182. Min Act: -0.1700

Data Index: 5466339 (Open Web Text)

Max Activating Token Index: 627

Text #19

Max Range: 4.2294. Min Range: -4.2294

Max Act: 3.9853. Min Act: -0.1700

Data Index: 785644 (Open Web Text)

Max Activating Token Index: 364