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

Dataset: Open Web Text

Neuron 1985 in Layer 5

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: 4.6824. Min Range: -4.6824

Max Act: 4.6824. Min Act: -0.1700

Data Index: 4097478 (Open Web Text)

Max Activating Token Index: 581

Text #1

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.6660. Min Act: -0.1700

Data Index: 1231106 (Open Web Text)

Max Activating Token Index: 964

Text #2

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.5221. Min Act: -0.1700

Data Index: 4575484 (Open Web Text)

Max Activating Token Index: 948

Text #3

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.4493. Min Act: -0.1700

Data Index: 1886784 (Open Web Text)

Max Activating Token Index: 1013

Text #4

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.4725. Min Act: -0.1700

Data Index: 5385758 (Open Web Text)

Max Activating Token Index: 311

Text #5

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.4688. Min Act: -0.1700

Data Index: 5609713 (Open Web Text)

Max Activating Token Index: 802

Text #6

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.4436. Min Act: -0.1700

Data Index: 5924981 (Open Web Text)

Max Activating Token Index: 318

Text #7

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.4140. Min Act: -0.1700

Data Index: 3515860 (Open Web Text)

Max Activating Token Index: 148

Text #8

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.3498. Min Act: -0.1700

Data Index: 899655 (Open Web Text)

Max Activating Token Index: 216

Text #9

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.3814. Min Act: -0.1700

Data Index: 2790111 (Open Web Text)

Max Activating Token Index: 992

Text #10

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.3574. Min Act: -0.1700

Data Index: 7687408 (Open Web Text)

Max Activating Token Index: 147

Text #11

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.3711. Min Act: -0.1700

Data Index: 4050962 (Open Web Text)

Max Activating Token Index: 757

Text #12

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.3558. Min Act: -0.1700

Data Index: 5903962 (Open Web Text)

Max Activating Token Index: 741

Text #13

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.3446. Min Act: -0.1700

Data Index: 939563 (Open Web Text)

Max Activating Token Index: 139

Text #14

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.3515. Min Act: -0.1700

Data Index: 7178285 (Open Web Text)

Max Activating Token Index: 237

Text #15

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.3668. Min Act: -0.1700

Data Index: 6585662 (Open Web Text)

Max Activating Token Index: 1021

Text #16

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.3224. Min Act: -0.1700

Data Index: 8813631 (Open Web Text)

Max Activating Token Index: 817

Text #17

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.3159. Min Act: -0.1700

Data Index: 1596525 (Open Web Text)

Max Activating Token Index: 395

Text #18

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.3204. Min Act: -0.1700

Data Index: 6377687 (Open Web Text)

Max Activating Token Index: 922

Text #19

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.2572. Min Act: -0.1700

Data Index: 559845 (Open Web Text)

Max Activating Token Index: 834