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

Dataset: Open Web Text

Neuron 200 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: 3.9773. Min Range: -3.9773

Max Act: 3.9578. Min Act: -0.1700

Data Index: 8394709 (Open Web Text)

Max Activating Token Index: 211

Text #1

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.9773. Min Act: -0.1700

Data Index: 2497716 (Open Web Text)

Max Activating Token Index: 889

Text #2

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.9562. Min Act: -0.1700

Data Index: 3746204 (Open Web Text)

Max Activating Token Index: 616

Text #3

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.9666. Min Act: -0.1700

Data Index: 915603 (Open Web Text)

Max Activating Token Index: 225

Text #4

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.9333. Min Act: -0.1700

Data Index: 1693410 (Open Web Text)

Max Activating Token Index: 839

Text #5

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.8872. Min Act: -0.1700

Data Index: 5640647 (Open Web Text)

Max Activating Token Index: 560

Text #6

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.9608. Min Act: -0.1700

Data Index: 4322685 (Open Web Text)

Max Activating Token Index: 760

Text #7

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.8788. Min Act: -0.1700

Data Index: 1895689 (Open Web Text)

Max Activating Token Index: 59

Text #8

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.8291. Min Act: -0.1700

Data Index: 8806815 (Open Web Text)

Max Activating Token Index: 581

Text #9

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.8836. Min Act: -0.1700

Data Index: 8075467 (Open Web Text)

Max Activating Token Index: 434

Text #10

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.8763. Min Act: -0.1700

Data Index: 6315617 (Open Web Text)

Max Activating Token Index: 133

Text #11

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.8572. Min Act: -0.1700

Data Index: 604737 (Open Web Text)

Max Activating Token Index: 456

Text #12

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.8469. Min Act: -0.1700

Data Index: 1767025 (Open Web Text)

Max Activating Token Index: 198

Text #13

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.8376. Min Act: -0.1700

Data Index: 7125424 (Open Web Text)

Max Activating Token Index: 505

Text #14

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.8094. Min Act: -0.1700

Data Index: 3228450 (Open Web Text)

Max Activating Token Index: 575

Text #15

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.7877. Min Act: -0.1700

Data Index: 5268323 (Open Web Text)

Max Activating Token Index: 721

Text #16

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.8471. Min Act: -0.1700

Data Index: 4557942 (Open Web Text)

Max Activating Token Index: 377

Text #17

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.8027. Min Act: -0.1700

Data Index: 6199794 (Open Web Text)

Max Activating Token Index: 562

Text #18

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.8154. Min Act: -0.1700

Data Index: 2915458 (Open Web Text)

Max Activating Token Index: 43

Text #19

Max Range: 3.9773. Min Range: -3.9773

Max Act: 3.8129. Min Act: -0.1700

Data Index: 1950940 (Open Web Text)

Max Activating Token Index: 65