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

Dataset: Open Web Text

Neuron 1821 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: 4.7039. Min Range: -4.7039

Max Act: 4.6618. Min Act: -0.1700

Data Index: 5051735 (Open Web Text)

Max Activating Token Index: 375

Text #1

Max Range: 4.7039. Min Range: -4.7039

Max Act: 4.7039. Min Act: -0.1700

Data Index: 8056768 (Open Web Text)

Max Activating Token Index: 784

Text #2

Max Range: 4.7039. Min Range: -4.7039

Max Act: 4.5919. Min Act: -0.1700

Data Index: 8442472 (Open Web Text)

Max Activating Token Index: 66

Text #3

Max Range: 4.7039. Min Range: -4.7039

Max Act: 4.5830. Min Act: -0.1700

Data Index: 5761772 (Open Web Text)

Max Activating Token Index: 327

Text #4

Max Range: 4.7039. Min Range: -4.7039

Max Act: 4.5787. Min Act: -0.1700

Data Index: 5006798 (Open Web Text)

Max Activating Token Index: 110

Text #5

Max Range: 4.7039. Min Range: -4.7039

Max Act: 4.5215. Min Act: -0.1700

Data Index: 1794425 (Open Web Text)

Max Activating Token Index: 169

Text #6

Max Range: 4.7039. Min Range: -4.7039

Max Act: 4.5405. Min Act: -0.1700

Data Index: 4070505 (Open Web Text)

Max Activating Token Index: 106

Text #7

Max Range: 4.7039. Min Range: -4.7039

Max Act: 4.5447. Min Act: -0.1700

Data Index: 4492186 (Open Web Text)

Max Activating Token Index: 565

Text #8

Max Range: 4.7039. Min Range: -4.7039

Max Act: 4.5352. Min Act: -0.1700

Data Index: 6206466 (Open Web Text)

Max Activating Token Index: 358

Text #9

Max Range: 4.7039. Min Range: -4.7039

Max Act: 4.5445. Min Act: -0.1700

Data Index: 8297406 (Open Web Text)

Max Activating Token Index: 979

Text #10

Max Range: 4.7039. Min Range: -4.7039

Max Act: 4.5232. Min Act: -0.1700

Data Index: 2460958 (Open Web Text)

Max Activating Token Index: 318

Text #11

Max Range: 4.7039. Min Range: -4.7039

Max Act: 4.4991. Min Act: -0.1700

Data Index: 6624085 (Open Web Text)

Max Activating Token Index: 920

Text #12

Max Range: 4.7039. Min Range: -4.7039

Max Act: 4.5310. Min Act: -0.1700

Data Index: 8763757 (Open Web Text)

Max Activating Token Index: 279

Text #13

Max Range: 4.7039. Min Range: -4.7039

Max Act: 4.5348. Min Act: -0.1700

Data Index: 2357630 (Open Web Text)

Max Activating Token Index: 161

Text #14

Max Range: 4.7039. Min Range: -4.7039

Max Act: 4.5056. Min Act: -0.1700

Data Index: 7557762 (Open Web Text)

Max Activating Token Index: 585

Text #15

Max Range: 4.7039. Min Range: -4.7039

Max Act: 4.4390. Min Act: -0.1700

Data Index: 7636773 (Open Web Text)

Max Activating Token Index: 417

Text #16

Max Range: 4.7039. Min Range: -4.7039

Max Act: 4.5175. Min Act: -0.1700

Data Index: 611144 (Open Web Text)

Max Activating Token Index: 618

Text #17

Max Range: 4.7039. Min Range: -4.7039

Max Act: 4.4970. Min Act: -0.1700

Data Index: 3138162 (Open Web Text)

Max Activating Token Index: 484

Text #18

Max Range: 4.7039. Min Range: -4.7039

Max Act: 4.4745. Min Act: -0.1700

Data Index: 128609 (Open Web Text)

Max Activating Token Index: 844

Text #19

Max Range: 4.7039. Min Range: -4.7039

Max Act: 4.4746. Min Act: -0.1700

Data Index: 7574141 (Open Web Text)

Max Activating Token Index: 1005