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

Dataset: Open Web Text

Neuron 624 in Layer 4

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: 3.6941. Min Range: -3.6941

Max Act: 3.6941. Min Act: -0.1700

Data Index: 4146499 (Open Web Text)

Max Activating Token Index: 641

Text #1

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.6834. Min Act: -0.1700

Data Index: 8475901 (Open Web Text)

Max Activating Token Index: 940

Text #2

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.6674. Min Act: -0.1700

Data Index: 2674086 (Open Web Text)

Max Activating Token Index: 659

Text #3

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.6809. Min Act: -0.1700

Data Index: 4782620 (Open Web Text)

Max Activating Token Index: 645

Text #4

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.6743. Min Act: -0.1700

Data Index: 2118142 (Open Web Text)

Max Activating Token Index: 271

Text #5

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.6529. Min Act: -0.1700

Data Index: 5993794 (Open Web Text)

Max Activating Token Index: 397

Text #6

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.6730. Min Act: -0.1700

Data Index: 2667013 (Open Web Text)

Max Activating Token Index: 550

Text #7

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.6519. Min Act: -0.1700

Data Index: 5942431 (Open Web Text)

Max Activating Token Index: 194

Text #8

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.6362. Min Act: -0.1700

Data Index: 6178950 (Open Web Text)

Max Activating Token Index: 108

Text #9

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.6358. Min Act: -0.1700

Data Index: 5784442 (Open Web Text)

Max Activating Token Index: 35

Text #10

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.6027. Min Act: -0.1700

Data Index: 7383031 (Open Web Text)

Max Activating Token Index: 1001

Text #11

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.5969. Min Act: -0.1700

Data Index: 240396 (Open Web Text)

Max Activating Token Index: 984

Text #12

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.5973. Min Act: -0.1700

Data Index: 6712959 (Open Web Text)

Max Activating Token Index: 566

Text #13

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.5913. Min Act: -0.1700

Data Index: 3063775 (Open Web Text)

Max Activating Token Index: 639

Text #14

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.5979. Min Act: -0.1700

Data Index: 5174190 (Open Web Text)

Max Activating Token Index: 57

Text #15

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.6109. Min Act: -0.1700

Data Index: 5329738 (Open Web Text)

Max Activating Token Index: 1016

Text #16

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.5974. Min Act: -0.1700

Data Index: 2726591 (Open Web Text)

Max Activating Token Index: 782

Text #17

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.5923. Min Act: -0.1700

Data Index: 8073670 (Open Web Text)

Max Activating Token Index: 606

Text #18

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.5949. Min Act: -0.1700

Data Index: 7635265 (Open Web Text)

Max Activating Token Index: 115

Text #19

Max Range: 3.6941. Min Range: -3.6941

Max Act: 3.5709. Min Act: -0.1700

Data Index: 1726512 (Open Web Text)

Max Activating Token Index: 99