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

Dataset: Open Web Text

Neuron 2157 in Layer 3

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: 3.2393. Min Range: -3.2393

Max Act: 3.2393. Min Act: -0.1700

Data Index: 5603131 (Open Web Text)

Max Activating Token Index: 822

Text #1

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.0596. Min Act: -0.1700

Data Index: 2059393 (Open Web Text)

Max Activating Token Index: 619

Text #2

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.0587. Min Act: -0.1700

Data Index: 6020961 (Open Web Text)

Max Activating Token Index: 447

Text #3

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.0400. Min Act: -0.1700

Data Index: 2070035 (Open Web Text)

Max Activating Token Index: 560

Text #4

Max Range: 3.2393. Min Range: -3.2393

Max Act: 3.0404. Min Act: -0.1700

Data Index: 2449367 (Open Web Text)

Max Activating Token Index: 881

Text #5

Max Range: 3.2393. Min Range: -3.2393

Max Act: 2.9996. Min Act: -0.1700

Data Index: 3195268 (Open Web Text)

Max Activating Token Index: 435

Text #6

Max Range: 3.2393. Min Range: -3.2393

Max Act: 2.9834. Min Act: -0.1700

Data Index: 1551049 (Open Web Text)

Max Activating Token Index: 1019

Text #7

Max Range: 3.2393. Min Range: -3.2393

Max Act: 2.9783. Min Act: -0.1700

Data Index: 8828989 (Open Web Text)

Max Activating Token Index: 123

Text #8

Max Range: 3.2393. Min Range: -3.2393

Max Act: 2.9132. Min Act: -0.1700

Data Index: 8432137 (Open Web Text)

Max Activating Token Index: 124

Text #9

Max Range: 3.2393. Min Range: -3.2393

Max Act: 2.9609. Min Act: -0.1700

Data Index: 8106461 (Open Web Text)

Max Activating Token Index: 551

Text #10

Max Range: 3.2393. Min Range: -3.2393

Max Act: 2.9303. Min Act: -0.1700

Data Index: 681460 (Open Web Text)

Max Activating Token Index: 121

Text #11

Max Range: 3.2393. Min Range: -3.2393

Max Act: 2.9260. Min Act: -0.1700

Data Index: 8437915 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.2393. Min Range: -3.2393

Max Act: 2.9258. Min Act: -0.1700

Data Index: 7796421 (Open Web Text)

Max Activating Token Index: 610

Text #13

Max Range: 3.2393. Min Range: -3.2393

Max Act: 2.9025. Min Act: -0.1700

Data Index: 2249680 (Open Web Text)

Max Activating Token Index: 934

Text #14

Max Range: 3.2393. Min Range: -3.2393

Max Act: 2.9097. Min Act: -0.1700

Data Index: 5046897 (Open Web Text)

Max Activating Token Index: 639

Text #15

Max Range: 3.2393. Min Range: -3.2393

Max Act: 2.8808. Min Act: -0.1700

Data Index: 7633114 (Open Web Text)

Max Activating Token Index: 698

Text #16

Max Range: 3.2393. Min Range: -3.2393

Max Act: 2.8889. Min Act: -0.1700

Data Index: 996172 (Open Web Text)

Max Activating Token Index: 936

Text #17

Max Range: 3.2393. Min Range: -3.2393

Max Act: 2.9032. Min Act: -0.1700

Data Index: 6953367 (Open Web Text)

Max Activating Token Index: 965

Text #18

Max Range: 3.2393. Min Range: -3.2393

Max Act: 2.8841. Min Act: -0.1700

Data Index: 6029670 (Open Web Text)

Max Activating Token Index: 90

Text #19

Max Range: 3.2393. Min Range: -3.2393

Max Act: 2.8681. Min Act: -0.1700

Data Index: 5179390 (Open Web Text)

Max Activating Token Index: 389