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

Dataset: Open Web Text

Neuron 1972 in Layer 2

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: 5.3054. Min Range: -5.3054

Max Act: 5.3054. Min Act: -0.1700

Data Index: 838964 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 5.3054. Min Range: -5.3054

Max Act: 5.2566. Min Act: -0.1700

Data Index: 3352019 (Open Web Text)

Max Activating Token Index: 304

Text #2

Max Range: 5.3054. Min Range: -5.3054

Max Act: 5.1979. Min Act: -0.1699

Data Index: 7545768 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 5.3054. Min Range: -5.3054

Max Act: 5.2258. Min Act: -0.1700

Data Index: 8207436 (Open Web Text)

Max Activating Token Index: 410

Text #4

Max Range: 5.3054. Min Range: -5.3054

Max Act: 5.2424. Min Act: -0.1700

Data Index: 3360280 (Open Web Text)

Max Activating Token Index: 492

Text #5

Max Range: 5.3054. Min Range: -5.3054

Max Act: 5.1364. Min Act: -0.1700

Data Index: 1508772 (Open Web Text)

Max Activating Token Index: 367

Text #6

Max Range: 5.3054. Min Range: -5.3054

Max Act: 5.1754. Min Act: -0.1700

Data Index: 370474 (Open Web Text)

Max Activating Token Index: 910

Text #7

Max Range: 5.3054. Min Range: -5.3054

Max Act: 5.1504. Min Act: -0.1700

Data Index: 5556868 (Open Web Text)

Max Activating Token Index: 247

Text #8

Max Range: 5.3054. Min Range: -5.3054

Max Act: 5.1433. Min Act: -0.1700

Data Index: 3237781 (Open Web Text)

Max Activating Token Index: 921

Text #9

Max Range: 5.3054. Min Range: -5.3054

Max Act: 5.1344. Min Act: -0.1700

Data Index: 727546 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 5.3054. Min Range: -5.3054

Max Act: 5.1090. Min Act: -0.1700

Data Index: 2060742 (Open Web Text)

Max Activating Token Index: 920

Text #11

Max Range: 5.3054. Min Range: -5.3054

Max Act: 5.0665. Min Act: -0.1700

Data Index: 2070425 (Open Web Text)

Max Activating Token Index: 686

Text #12

Max Range: 5.3054. Min Range: -5.3054

Max Act: 5.2022. Min Act: -0.1700

Data Index: 1366590 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 5.3054. Min Range: -5.3054

Max Act: 5.0866. Min Act: -0.1700

Data Index: 5859793 (Open Web Text)

Max Activating Token Index: 144

Text #14

Max Range: 5.3054. Min Range: -5.3054

Max Act: 5.1021. Min Act: -0.1700

Data Index: 7512402 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 5.3054. Min Range: -5.3054

Max Act: 5.0722. Min Act: -0.1700

Data Index: 2941412 (Open Web Text)

Max Activating Token Index: 403

Text #16

Max Range: 5.3054. Min Range: -5.3054

Max Act: 5.1313. Min Act: -0.1700

Data Index: 3042553 (Open Web Text)

Max Activating Token Index: 669

Text #17

Max Range: 5.3054. Min Range: -5.3054

Max Act: 5.0792. Min Act: -0.1700

Data Index: 5179557 (Open Web Text)

Max Activating Token Index: 396

Text #18

Max Range: 5.3054. Min Range: -5.3054

Max Act: 5.0742. Min Act: -0.1700

Data Index: 5138940 (Open Web Text)

Max Activating Token Index: 563

Text #19

Max Range: 5.3054. Min Range: -5.3054

Max Act: 5.1926. Min Act: -0.1700

Data Index: 1738943 (Open Web Text)

Max Activating Token Index: 1023