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

Dataset: Open Web Text

Neuron 1412 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: 4.2920. Min Range: -4.2920

Max Act: 4.2920. Min Act: -0.1700

Data Index: 7877660 (Open Web Text)

Max Activating Token Index: 624

Text #1

Max Range: 4.2920. Min Range: -4.2920

Max Act: 4.1930. Min Act: -0.1700

Data Index: 7334497 (Open Web Text)

Max Activating Token Index: 366

Text #2

Max Range: 4.2920. Min Range: -4.2920

Max Act: 4.2200. Min Act: -0.1700

Data Index: 4382646 (Open Web Text)

Max Activating Token Index: 888

Text #3

Max Range: 4.2920. Min Range: -4.2920

Max Act: 4.1944. Min Act: -0.1700

Data Index: 4736615 (Open Web Text)

Max Activating Token Index: 752

Text #4

Max Range: 4.2920. Min Range: -4.2920

Max Act: 4.1423. Min Act: -0.1700

Data Index: 7138671 (Open Web Text)

Max Activating Token Index: 753

Text #5

Max Range: 4.2920. Min Range: -4.2920

Max Act: 4.1900. Min Act: -0.1700

Data Index: 2052421 (Open Web Text)

Max Activating Token Index: 945

Text #6

Max Range: 4.2920. Min Range: -4.2920

Max Act: 4.1555. Min Act: -0.1700

Data Index: 4641456 (Open Web Text)

Max Activating Token Index: 286

Text #7

Max Range: 4.2920. Min Range: -4.2920

Max Act: 4.0903. Min Act: -0.1700

Data Index: 5745516 (Open Web Text)

Max Activating Token Index: 1013

Text #8

Max Range: 4.2920. Min Range: -4.2920

Max Act: 4.1443. Min Act: -0.1700

Data Index: 1897174 (Open Web Text)

Max Activating Token Index: 299

Text #9

Max Range: 4.2920. Min Range: -4.2920

Max Act: 4.1359. Min Act: -0.1700

Data Index: 3361520 (Open Web Text)

Max Activating Token Index: 309

Text #10

Max Range: 4.2920. Min Range: -4.2920

Max Act: 4.1528. Min Act: -0.1700

Data Index: 2801877 (Open Web Text)

Max Activating Token Index: 124

Text #11

Max Range: 4.2920. Min Range: -4.2920

Max Act: 4.1438. Min Act: -0.1700

Data Index: 8532076 (Open Web Text)

Max Activating Token Index: 306

Text #12

Max Range: 4.2920. Min Range: -4.2920

Max Act: 4.1406. Min Act: -0.1700

Data Index: 6621301 (Open Web Text)

Max Activating Token Index: 552

Text #13

Max Range: 4.2920. Min Range: -4.2920

Max Act: 4.0852. Min Act: -0.1700

Data Index: 635032 (Open Web Text)

Max Activating Token Index: 357

Text #14

Max Range: 4.2920. Min Range: -4.2920

Max Act: 4.1209. Min Act: -0.1700

Data Index: 1595325 (Open Web Text)

Max Activating Token Index: 807

Text #15

Max Range: 4.2920. Min Range: -4.2920

Max Act: 4.0752. Min Act: -0.1700

Data Index: 1029967 (Open Web Text)

Max Activating Token Index: 757

Text #16

Max Range: 4.2920. Min Range: -4.2920

Max Act: 4.1295. Min Act: -0.1700

Data Index: 2324528 (Open Web Text)

Max Activating Token Index: 355

Text #17

Max Range: 4.2920. Min Range: -4.2920

Max Act: 4.1129. Min Act: -0.1700

Data Index: 4288803 (Open Web Text)

Max Activating Token Index: 179

Text #18

Max Range: 4.2920. Min Range: -4.2920

Max Act: 4.0604. Min Act: -0.1700

Data Index: 1506670 (Open Web Text)

Max Activating Token Index: 414

Text #19

Max Range: 4.2920. Min Range: -4.2920

Max Act: 4.0720. Min Act: -0.1700

Data Index: 279379 (Open Web Text)

Max Activating Token Index: 307