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

Dataset: Open Web Text

Neuron 106 in Layer 1

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: 4.6726. Min Range: -4.6726

Max Act: 4.6418. Min Act: -0.1700

Data Index: 2629285 (Open Web Text)

Max Activating Token Index: 906

Text #1

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.6717. Min Act: -0.1700

Data Index: 7961600 (Open Web Text)

Max Activating Token Index: 990

Text #2

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.6726. Min Act: -0.1700

Data Index: 1164942 (Open Web Text)

Max Activating Token Index: 497

Text #3

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.6545. Min Act: -0.1700

Data Index: 8428148 (Open Web Text)

Max Activating Token Index: 435

Text #4

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.6471. Min Act: -0.1700

Data Index: 6112907 (Open Web Text)

Max Activating Token Index: 175

Text #5

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.6080. Min Act: -0.1700

Data Index: 183619 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5898. Min Act: -0.1700

Data Index: 3431789 (Open Web Text)

Max Activating Token Index: 422

Text #7

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5665. Min Act: -0.1700

Data Index: 2364530 (Open Web Text)

Max Activating Token Index: 767

Text #8

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5775. Min Act: -0.1700

Data Index: 5363360 (Open Web Text)

Max Activating Token Index: 708

Text #9

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5783. Min Act: -0.1700

Data Index: 5846768 (Open Web Text)

Max Activating Token Index: 515

Text #10

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5563. Min Act: -0.1700

Data Index: 8111022 (Open Web Text)

Max Activating Token Index: 553

Text #11

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5591. Min Act: -0.1700

Data Index: 82288 (Open Web Text)

Max Activating Token Index: 507

Text #12

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5439. Min Act: -0.1700

Data Index: 5424437 (Open Web Text)

Max Activating Token Index: 430

Text #13

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5434. Min Act: -0.1700

Data Index: 2629284 (Open Web Text)

Max Activating Token Index: 808

Text #14

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5206. Min Act: -0.1700

Data Index: 422699 (Open Web Text)

Max Activating Token Index: 985

Text #15

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5240. Min Act: -0.1700

Data Index: 361042 (Open Web Text)

Max Activating Token Index: 602

Text #16

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.4846. Min Act: -0.1700

Data Index: 8196689 (Open Web Text)

Max Activating Token Index: 783

Text #17

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5134. Min Act: -0.1700

Data Index: 270756 (Open Web Text)

Max Activating Token Index: 191

Text #18

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5044. Min Act: -0.1700

Data Index: 2166102 (Open Web Text)

Max Activating Token Index: 930

Text #19

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.4783. Min Act: -0.1700

Data Index: 1347042 (Open Web Text)

Max Activating Token Index: 780