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

Dataset: Open Web Text

Neuron 952 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: 4.7382. Min Range: -4.7382

Max Act: 4.7382. Min Act: -0.1700

Data Index: 5357544 (Open Web Text)

Max Activating Token Index: 177

Text #1

Max Range: 4.7382. Min Range: -4.7382

Max Act: 4.6110. Min Act: -0.1700

Data Index: 3435882 (Open Web Text)

Max Activating Token Index: 24

Text #2

Max Range: 4.7382. Min Range: -4.7382

Max Act: 4.5336. Min Act: -0.1700

Data Index: 433743 (Open Web Text)

Max Activating Token Index: 18

Text #3

Max Range: 4.7382. Min Range: -4.7382

Max Act: 4.5146. Min Act: -0.1700

Data Index: 6614815 (Open Web Text)

Max Activating Token Index: 562

Text #4

Max Range: 4.7382. Min Range: -4.7382

Max Act: 4.4911. Min Act: -0.1700

Data Index: 3060285 (Open Web Text)

Max Activating Token Index: 515

Text #5

Max Range: 4.7382. Min Range: -4.7382

Max Act: 4.4935. Min Act: -0.1700

Data Index: 6207884 (Open Web Text)

Max Activating Token Index: 719

Text #6

Max Range: 4.7382. Min Range: -4.7382

Max Act: 4.4486. Min Act: -0.1700

Data Index: 8733907 (Open Web Text)

Max Activating Token Index: 1008

Text #7

Max Range: 4.7382. Min Range: -4.7382

Max Act: 4.4552. Min Act: -0.1700

Data Index: 411648 (Open Web Text)

Max Activating Token Index: 940

Text #8

Max Range: 4.7382. Min Range: -4.7382

Max Act: 4.4685. Min Act: -0.1700

Data Index: 5581093 (Open Web Text)

Max Activating Token Index: 51

Text #9

Max Range: 4.7382. Min Range: -4.7382

Max Act: 4.4145. Min Act: -0.1700

Data Index: 11006 (Open Web Text)

Max Activating Token Index: 63

Text #10

Max Range: 4.7382. Min Range: -4.7382

Max Act: 4.4224. Min Act: -0.1700

Data Index: 1723991 (Open Web Text)

Max Activating Token Index: 15

Text #11

Max Range: 4.7382. Min Range: -4.7382

Max Act: 4.4380. Min Act: -0.1700

Data Index: 2523265 (Open Web Text)

Max Activating Token Index: 916

Text #12

Max Range: 4.7382. Min Range: -4.7382

Max Act: 4.4113. Min Act: -0.1700

Data Index: 3173536 (Open Web Text)

Max Activating Token Index: 547

Text #13

Max Range: 4.7382. Min Range: -4.7382

Max Act: 4.4432. Min Act: -0.1700

Data Index: 2015743 (Open Web Text)

Max Activating Token Index: 674

Text #14

Max Range: 4.7382. Min Range: -4.7382

Max Act: 4.4345. Min Act: -0.1700

Data Index: 4752938 (Open Web Text)

Max Activating Token Index: 79

Text #15

Max Range: 4.7382. Min Range: -4.7382

Max Act: 4.4261. Min Act: -0.1700

Data Index: 4138238 (Open Web Text)

Max Activating Token Index: 431

Text #16

Max Range: 4.7382. Min Range: -4.7382

Max Act: 4.3785. Min Act: -0.1700

Data Index: 6486970 (Open Web Text)

Max Activating Token Index: 920

Text #17

Max Range: 4.7382. Min Range: -4.7382

Max Act: 4.3957. Min Act: -0.1700

Data Index: 5499019 (Open Web Text)

Max Activating Token Index: 25

Text #18

Max Range: 4.7382. Min Range: -4.7382

Max Act: 4.3733. Min Act: -0.1700

Data Index: 2740309 (Open Web Text)

Max Activating Token Index: 748

Text #19

Max Range: 4.7382. Min Range: -4.7382

Max Act: 4.4164. Min Act: -0.1700

Data Index: 7628844 (Open Web Text)

Max Activating Token Index: 519