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

Dataset: Open Web Text

Neuron 291 in Layer 0

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: 2.9008. Min Range: -2.9008

Max Act: 2.9008. Min Act: -0.1700

Data Index: 907393 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.9008. Min Range: -2.9008

Max Act: 2.8724. Min Act: -0.1700

Data Index: 5319212 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 2.9008. Min Range: -2.9008

Max Act: 2.8919. Min Act: -0.1700

Data Index: 5082203 (Open Web Text)

Max Activating Token Index: 841

Text #3

Max Range: 2.9008. Min Range: -2.9008

Max Act: 2.8633. Min Act: -0.1700

Data Index: 896215 (Open Web Text)

Max Activating Token Index: 815

Text #4

Max Range: 2.9008. Min Range: -2.9008

Max Act: 2.8487. Min Act: -0.1700

Data Index: 3431518 (Open Web Text)

Max Activating Token Index: 844

Text #5

Max Range: 2.9008. Min Range: -2.9008

Max Act: 2.8596. Min Act: -0.1700

Data Index: 6061666 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.9008. Min Range: -2.9008

Max Act: 2.8550. Min Act: -0.1700

Data Index: 7579788 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.9008. Min Range: -2.9008

Max Act: 2.8596. Min Act: -0.1700

Data Index: 2031951 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.9008. Min Range: -2.9008

Max Act: 2.8476. Min Act: -0.1700

Data Index: 4437016 (Open Web Text)

Max Activating Token Index: 915

Text #9

Max Range: 2.9008. Min Range: -2.9008

Max Act: 2.8337. Min Act: -0.1700

Data Index: 1971505 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.9008. Min Range: -2.9008

Max Act: 2.8328. Min Act: -0.1698

Data Index: 161406 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.9008. Min Range: -2.9008

Max Act: 2.8207. Min Act: -0.1700

Data Index: 849098 (Open Web Text)

Max Activating Token Index: 485

Text #12

Max Range: 2.9008. Min Range: -2.9008

Max Act: 2.8377. Min Act: -0.1700

Data Index: 5027743 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 2.9008. Min Range: -2.9008

Max Act: 2.8264. Min Act: -0.1700

Data Index: 4694541 (Open Web Text)

Max Activating Token Index: 964

Text #14

Max Range: 2.9008. Min Range: -2.9008

Max Act: 2.8155. Min Act: -0.1700

Data Index: 1475070 (Open Web Text)

Max Activating Token Index: 832

Text #15

Max Range: 2.9008. Min Range: -2.9008

Max Act: 2.8113. Min Act: -0.1700

Data Index: 4559409 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 2.9008. Min Range: -2.9008

Max Act: 2.8330. Min Act: -0.1700

Data Index: 4323967 (Open Web Text)

Max Activating Token Index: 764

Text #17

Max Range: 2.9008. Min Range: -2.9008

Max Act: 2.8130. Min Act: -0.1700

Data Index: 4269142 (Open Web Text)

Max Activating Token Index: 986

Text #18

Max Range: 2.9008. Min Range: -2.9008

Max Act: 2.8132. Min Act: -0.1700

Data Index: 141143 (Open Web Text)

Max Activating Token Index: 796

Text #19

Max Range: 2.9008. Min Range: -2.9008

Max Act: 2.8061. Min Act: -0.1700

Data Index: 3761385 (Open Web Text)

Max Activating Token Index: 6