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

Dataset: Open Web Text

Neuron 3000 in Layer 2

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: 4.2605. Min Range: -4.2605

Max Act: 4.2605. Min Act: -0.1700

Data Index: 3376636 (Open Web Text)

Max Activating Token Index: 313

Text #1

Max Range: 4.2605. Min Range: -4.2605

Max Act: 4.2530. Min Act: -0.1700

Data Index: 3410759 (Open Web Text)

Max Activating Token Index: 751

Text #2

Max Range: 4.2605. Min Range: -4.2605

Max Act: 4.2270. Min Act: -0.1700

Data Index: 1866242 (Open Web Text)

Max Activating Token Index: 855

Text #3

Max Range: 4.2605. Min Range: -4.2605

Max Act: 4.2298. Min Act: -0.1700

Data Index: 2246512 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.2605. Min Range: -4.2605

Max Act: 4.2033. Min Act: -0.1700

Data Index: 1121739 (Open Web Text)

Max Activating Token Index: 981

Text #5

Max Range: 4.2605. Min Range: -4.2605

Max Act: 4.1874. Min Act: -0.1700

Data Index: 5720689 (Open Web Text)

Max Activating Token Index: 1006

Text #6

Max Range: 4.2605. Min Range: -4.2605

Max Act: 4.2074. Min Act: -0.1700

Data Index: 6326402 (Open Web Text)

Max Activating Token Index: 461

Text #7

Max Range: 4.2605. Min Range: -4.2605

Max Act: 4.2294. Min Act: -0.1700

Data Index: 2403603 (Open Web Text)

Max Activating Token Index: 1015

Text #8

Max Range: 4.2605. Min Range: -4.2605

Max Act: 4.2394. Min Act: -0.1700

Data Index: 2145691 (Open Web Text)

Max Activating Token Index: 359

Text #9

Max Range: 4.2605. Min Range: -4.2605

Max Act: 4.2232. Min Act: -0.1700

Data Index: 7385686 (Open Web Text)

Max Activating Token Index: 644

Text #10

Max Range: 4.2605. Min Range: -4.2605

Max Act: 4.2025. Min Act: -0.1700

Data Index: 6925398 (Open Web Text)

Max Activating Token Index: 279

Text #11

Max Range: 4.2605. Min Range: -4.2605

Max Act: 4.1689. Min Act: -0.1700

Data Index: 1430377 (Open Web Text)

Max Activating Token Index: 345

Text #12

Max Range: 4.2605. Min Range: -4.2605

Max Act: 4.2000. Min Act: -0.1700

Data Index: 3286188 (Open Web Text)

Max Activating Token Index: 286

Text #13

Max Range: 4.2605. Min Range: -4.2605

Max Act: 4.2027. Min Act: -0.1700

Data Index: 3934887 (Open Web Text)

Max Activating Token Index: 791

Text #14

Max Range: 4.2605. Min Range: -4.2605

Max Act: 4.1829. Min Act: -0.1700

Data Index: 978640 (Open Web Text)

Max Activating Token Index: 601

Text #15

Max Range: 4.2605. Min Range: -4.2605

Max Act: 4.1941. Min Act: -0.1700

Data Index: 6334935 (Open Web Text)

Max Activating Token Index: 143

Text #16

Max Range: 4.2605. Min Range: -4.2605

Max Act: 4.1794. Min Act: -0.1700

Data Index: 2301814 (Open Web Text)

Max Activating Token Index: 415

Text #17

Max Range: 4.2605. Min Range: -4.2605

Max Act: 4.2072. Min Act: -0.1700

Data Index: 4055368 (Open Web Text)

Max Activating Token Index: 397

Text #18

Max Range: 4.2605. Min Range: -4.2605

Max Act: 4.1722. Min Act: -0.1700

Data Index: 3324606 (Open Web Text)

Max Activating Token Index: 830

Text #19

Max Range: 4.2605. Min Range: -4.2605

Max Act: 4.1499. Min Act: -0.1700

Data Index: 4051406 (Open Web Text)

Max Activating Token Index: 640