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

Dataset: Open Web Text

Neuron 1835 in Layer 6

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: 2.2605. Min Range: -2.2605

Max Act: 2.2477. Min Act: -0.1700

Data Index: 2677972 (Open Web Text)

Max Activating Token Index: 304

Text #1

Max Range: 2.2605. Min Range: -2.2605

Max Act: 2.2605. Min Act: -0.1700

Data Index: 6701105 (Open Web Text)

Max Activating Token Index: 994

Text #2

Max Range: 2.2605. Min Range: -2.2605

Max Act: 2.1833. Min Act: -0.1700

Data Index: 4513296 (Open Web Text)

Max Activating Token Index: 607

Text #3

Max Range: 2.2605. Min Range: -2.2605

Max Act: 2.1778. Min Act: -0.1700

Data Index: 2427904 (Open Web Text)

Max Activating Token Index: 427

Text #4

Max Range: 2.2605. Min Range: -2.2605

Max Act: 2.1968. Min Act: -0.1700

Data Index: 3874654 (Open Web Text)

Max Activating Token Index: 61

Text #5

Max Range: 2.2605. Min Range: -2.2605

Max Act: 2.1938. Min Act: -0.1700

Data Index: 865632 (Open Web Text)

Max Activating Token Index: 345

Text #6

Max Range: 2.2605. Min Range: -2.2605

Max Act: 2.1805. Min Act: -0.1700

Data Index: 8817562 (Open Web Text)

Max Activating Token Index: 292

Text #7

Max Range: 2.2605. Min Range: -2.2605

Max Act: 2.1807. Min Act: -0.1700

Data Index: 7505183 (Open Web Text)

Max Activating Token Index: 1011

Text #8

Max Range: 2.2605. Min Range: -2.2605

Max Act: 2.1622. Min Act: -0.1700

Data Index: 6537487 (Open Web Text)

Max Activating Token Index: 999

Text #9

Max Range: 2.2605. Min Range: -2.2605

Max Act: 2.1685. Min Act: -0.1700

Data Index: 4332182 (Open Web Text)

Max Activating Token Index: 700

Text #10

Max Range: 2.2605. Min Range: -2.2605

Max Act: 2.1729. Min Act: -0.1700

Data Index: 6076260 (Open Web Text)

Max Activating Token Index: 213

Text #11

Max Range: 2.2605. Min Range: -2.2605

Max Act: 2.1677. Min Act: -0.1700

Data Index: 2593379 (Open Web Text)

Max Activating Token Index: 854

Text #12

Max Range: 2.2605. Min Range: -2.2605

Max Act: 2.1850. Min Act: -0.1700

Data Index: 8035328 (Open Web Text)

Max Activating Token Index: 599

Text #13

Max Range: 2.2605. Min Range: -2.2605

Max Act: 2.1733. Min Act: -0.1700

Data Index: 5327616 (Open Web Text)

Max Activating Token Index: 748

Text #14

Max Range: 2.2605. Min Range: -2.2605

Max Act: 2.1676. Min Act: -0.1700

Data Index: 925488 (Open Web Text)

Max Activating Token Index: 90

Text #15

Max Range: 2.2605. Min Range: -2.2605

Max Act: 2.1524. Min Act: -0.1700

Data Index: 7441471 (Open Web Text)

Max Activating Token Index: 141

Text #16

Max Range: 2.2605. Min Range: -2.2605

Max Act: 2.1413. Min Act: -0.1700

Data Index: 6958106 (Open Web Text)

Max Activating Token Index: 289

Text #17

Max Range: 2.2605. Min Range: -2.2605

Max Act: 2.1324. Min Act: -0.1700

Data Index: 1707722 (Open Web Text)

Max Activating Token Index: 893

Text #18

Max Range: 2.2605. Min Range: -2.2605

Max Act: 2.1319. Min Act: -0.1700

Data Index: 6642662 (Open Web Text)

Max Activating Token Index: 805

Text #19

Max Range: 2.2605. Min Range: -2.2605

Max Act: 2.1317. Min Act: -0.1700

Data Index: 10702 (Open Web Text)

Max Activating Token Index: 252